Top 10 Arxiv Papers Today
2.647 Mikeys
#1. MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
Sungjoo Ha, Martin Kersner, Beomsu Kim, Seokjun Seo, Dongyoung Kim
When there is a mismatch between the target identity and the driver identity,
face reenactment suffers severe degradation in the quality of the result,
especially in a few-shot setting. The identity preservation problem, where the
model loses the detailed information of the target leading to a defective
output, is the most common failure mode. The problem has several potential
sources such as the identity of the driver leaking due to the identity
mismatch, or dealing with unseen large poses. To overcome such problems, we
introduce components that address the mentioned problem: image attention block,
target feature alignment, and landmark transformer. Through attending and
warping the relevant features, the proposed architecture, called MarioNETte,
produces high-quality reenactments of unseen identities in a few-shot setting.
In addition, the landmark transformer dramatically alleviates the identity
preservation problem by isolating the expression geometry through landmark
disentanglement. Comprehensive experiments are performed to...
more |
pdf
| html
Figures
None.
Tweets
shurain:
project page: https://t.co/8vf2LUWpoQ
paper: https://t.co/cUyLEMTfRB
video: https://t.co/CffU39CPjM
idgmatrix:
RT @roadrunning01: MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
pdf: https://t.co/FT0fUfPncC
abs: https://t.…
syoyo:
RT @roadrunning01: MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
pdf: https://t.co/FT0fUfPncC
abs: https://t.…
udoooom:
RT @roadrunning01: MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
pdf: https://t.co/FT0fUfPncC
abs: https://t.…
sei_shinagawa:
RT @roadrunning01: MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
pdf: https://t.co/FT0fUfPncC
abs: https://t.…
GiorgioPatrini:
RT @roadrunning01: MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
pdf: https://t.co/FT0fUfPncC
abs: https://t.…
KageKirin:
RT @roadrunning01: MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
pdf: https://t.co/FT0fUfPncC
abs: https://t.…
s_m__p_lls:
RT @roadrunning01: MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
pdf: https://t.co/FT0fUfPncC
abs: https://t.…
morioka:
RT @roadrunning01: MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
pdf: https://t.co/FT0fUfPncC
abs: https://t.…
SythonUK:
RT @roadrunning01: MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
pdf: https://t.co/FT0fUfPncC
abs: https://t.…
KouroshMeshgi:
RT @roadrunning01: MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
pdf: https://t.co/FT0fUfPncC
abs: https://t.…
YannLePaih:
RT @roadrunning01: MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
pdf: https://t.co/FT0fUfPncC
abs: https://t.…
dragonmeteor:
RT @roadrunning01: MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
pdf: https://t.co/FT0fUfPncC
abs: https://t.…
santiagoitzcoat:
RT @roadrunning01: MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
pdf: https://t.co/FT0fUfPncC
abs: https://t.…
uoe9981:
RT @roadrunning01: MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
pdf: https://t.co/FT0fUfPncC
abs: https://t.…
bhargavbardipur:
RT @roadrunning01: MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
pdf: https://t.co/FT0fUfPncC
abs: https://t.…
0oMetao0:
RT @roadrunning01: MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
pdf: https://t.co/FT0fUfPncC
abs: https://t.…
nving:
RT @roadrunning01: MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
pdf: https://t.co/FT0fUfPncC
abs: https://t.…
SHK_eolus:
RT @roadrunning01: MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
pdf: https://t.co/FT0fUfPncC
abs: https://t.…
jp_axs4ll:
RT @roadrunning01: MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
pdf: https://t.co/FT0fUfPncC
abs: https://t.…
AhnsikChoi:
RT @roadrunning01: MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
pdf: https://t.co/FT0fUfPncC
abs: https://t.…
gyultaste:
RT @shurain: project page: https://t.co/8vf2LUWpoQ
paper: https://t.co/cUyLEMTfRB
video: https://t.co/CffU39CPjM
honasu:
RT @roadrunning01: MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
pdf: https://t.co/FT0fUfPncC
abs: https://t.…
dannyehb:
RT @roadrunning01: MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
pdf: https://t.co/FT0fUfPncC
abs: https://t.…
MarkTan57229491:
RT @roadrunning01: MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
pdf: https://t.co/FT0fUfPncC
abs: https://t.…
veydpz_public:
RT @shurain: project page: https://t.co/8vf2LUWpoQ
paper: https://t.co/cUyLEMTfRB
video: https://t.co/CffU39CPjM
funxiah:
RT @roadrunning01: MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
pdf: https://t.co/FT0fUfPncC
abs: https://t.…
extratype:
RT @roadrunning01: MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
pdf: https://t.co/FT0fUfPncC
abs: https://t.…
AssistedEvolve:
RT @roadrunning01: MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
pdf: https://t.co/FT0fUfPncC
abs: https://t.…
jastner109:
RT @roadrunning01: MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
pdf: https://t.co/FT0fUfPncC
abs: https://t.…
krokrow:
RT @roadrunning01: MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
pdf: https://t.co/FT0fUfPncC
abs: https://t.…
starflo_cia:
RT @roadrunning01: MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
pdf: https://t.co/FT0fUfPncC
abs: https://t.…
fantra215:
RT @roadrunning01: MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
pdf: https://t.co/FT0fUfPncC
abs: https://t.…
helplessnature:
RT @roadrunning01: MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
pdf: https://t.co/FT0fUfPncC
abs: https://t.…
_jongwook_kim:
RT @roadrunning01: MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
pdf: https://t.co/FT0fUfPncC
abs: https://t.…
6_6kyul:
RT @roadrunning01: MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
pdf: https://t.co/FT0fUfPncC
abs: https://t.…
AndroidBlogger:
RT @roadrunning01: MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
pdf: https://t.co/FT0fUfPncC
abs: https://t.…
matthewopala:
RT @roadrunning01: MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
pdf: https://t.co/FT0fUfPncC
abs: https://t.…
coreaful:
RT @shurain: project page: https://t.co/8vf2LUWpoQ
paper: https://t.co/cUyLEMTfRB
video: https://t.co/CffU39CPjM
smizuka1:
RT @roadrunning01: MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
pdf: https://t.co/FT0fUfPncC
abs: https://t.…
albelwu:
RT @roadrunning01: MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
pdf: https://t.co/FT0fUfPncC
abs: https://t.…
wjdms20:
RT @roadrunning01: MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
pdf: https://t.co/FT0fUfPncC
abs: https://t.…
Malghamdi_AI:
RT @roadrunning01: MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
pdf: https://t.co/FT0fUfPncC
abs: https://t.…
UkiwhY:
RT @roadrunning01: MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
pdf: https://t.co/FT0fUfPncC
abs: https://t.…
jaesonglee:
RT @shurain: project page: https://t.co/8vf2LUWpoQ
paper: https://t.co/cUyLEMTfRB
video: https://t.co/CffU39CPjM
MassBassLol:
RT @roadrunning01: MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
pdf: https://t.co/FT0fUfPncC
abs: https://t.…
robin_kips:
RT @roadrunning01: MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
pdf: https://t.co/FT0fUfPncC
abs: https://t.…
shukiiiii4:
RT @shurain: project page: https://t.co/8vf2LUWpoQ
paper: https://t.co/cUyLEMTfRB
video: https://t.co/CffU39CPjM
Github
None.
Youtube
None.
Other stats
Sample Sizes : None.
Authors: 5
Total Words: 0
Unqiue Words: 0
2.389 Mikeys
#2. VITON-GAN: Virtual Try-on Image Generator Trained with Adversarial Loss
Shion Honda
Generating a virtual try-on image from in-shop clothing images and a model
person's snapshot is a challenging task because the human body and clothes have
high flexibility in their shapes. In this paper, we develop a Virtual Try-on
Generative Adversarial Network (VITON-GAN), that generates virtual try-on
images using images of in-shop clothing and a model person. This method
enhances the quality of the generated image when occlusion is present in a
model person's image (e.g., arms crossed in front of the clothes) by adding an
adversarial mechanism in the training pipeline.
more |
pdf
| html
Figures
Tweets
roadrunning01:
VITON-GAN: Virtual Try-on Image Generator Trained with Adversarial Loss
pdf: https://t.co/dqqzab4tJX
abs: https://t.co/0ZG1dRSF8f
github: https://t.co/oaLnU4W01t https://t.co/mvytbaPUBm
shion_honda:
The preprint version of our short paper "VITON-GAN: Virtual Try-on Image Generator Trained with Adversarial Loss" is now on arXiv!
This work was presented at the EuroGraphics 2019 poster session.
https://t.co/lJy8ZmCBKD https://t.co/Q11777aLRN
yshhrknmr:
RT @roadrunning01: VITON-GAN: Virtual Try-on Image Generator Trained with Adversarial Loss
pdf: https://t.co/dqqzab4tJX
abs: https://t.co/0…
shion_honda:
RT @roadrunning01: VITON-GAN: Virtual Try-on Image Generator Trained with Adversarial Loss
pdf: https://t.co/dqqzab4tJX
abs: https://t.co/0…
alxcnwy:
RT @roadrunning01: VITON-GAN: Virtual Try-on Image Generator Trained with Adversarial Loss
pdf: https://t.co/dqqzab4tJX
abs: https://t.co/0…
ialuronico:
RT @roadrunning01: VITON-GAN: Virtual Try-on Image Generator Trained with Adversarial Loss
pdf: https://t.co/dqqzab4tJX
abs: https://t.co/0…
fanks_vision:
RT @roadrunning01: VITON-GAN: Virtual Try-on Image Generator Trained with Adversarial Loss
pdf: https://t.co/dqqzab4tJX
abs: https://t.co/0…
briandixn:
RT @roadrunning01: VITON-GAN: Virtual Try-on Image Generator Trained with Adversarial Loss
pdf: https://t.co/dqqzab4tJX
abs: https://t.co/0…
AssistedEvolve:
RT @roadrunning01: VITON-GAN: Virtual Try-on Image Generator Trained with Adversarial Loss
pdf: https://t.co/dqqzab4tJX
abs: https://t.co/0…
Feldman1Michael:
RT @roadrunning01: VITON-GAN: Virtual Try-on Image Generator Trained with Adversarial Loss
pdf: https://t.co/dqqzab4tJX
abs: https://t.co/0…
summer4an:
RT @roadrunning01: VITON-GAN: Virtual Try-on Image Generator Trained with Adversarial Loss
pdf: https://t.co/dqqzab4tJX
abs: https://t.co/0…
Lei_Xu_:
RT @roadrunning01: VITON-GAN: Virtual Try-on Image Generator Trained with Adversarial Loss
pdf: https://t.co/dqqzab4tJX
abs: https://t.co/0…
hey_kishore:
RT @roadrunning01: VITON-GAN: Virtual Try-on Image Generator Trained with Adversarial Loss
pdf: https://t.co/dqqzab4tJX
abs: https://t.co/0…
UkiwhY:
RT @roadrunning01: VITON-GAN: Virtual Try-on Image Generator Trained with Adversarial Loss
pdf: https://t.co/dqqzab4tJX
abs: https://t.co/0…
MassBassLol:
RT @roadrunning01: VITON-GAN: Virtual Try-on Image Generator Trained with Adversarial Loss
pdf: https://t.co/dqqzab4tJX
abs: https://t.co/0…
Luck2john:
RT @roadrunning01: VITON-GAN: Virtual Try-on Image Generator Trained with Adversarial Loss
pdf: https://t.co/dqqzab4tJX
abs: https://t.co/0…
Github
Original implementation of the paper "VITON-GAN: Virtual Try-on Image Generator Trained with Adversarial Loss" by Shion Honda.
Stargazers: 10
Subscribers: 2
Subscribers: 2
Forks: 5
Open Issues: 1
Open Issues: 1
Youtube
None.
Other stats
Sample Sizes : None.
Authors: 1
Total Words: 970
Unqiue Words: 500
2.357 Mikeys
#3. Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
Julian Schrittwieser, Ioannis Antonoglou, Thomas Hubert, Karen Simonyan, Laurent Sifre, Simon Schmitt, Arthur Guez, Edward Lockhart, Demis Hassabis, Thore Graepel, Timothy Lillicrap, David Silver
Constructing agents with planning capabilities has long been one of the main
challenges in the pursuit of artificial intelligence. Tree-based planning
methods have enjoyed huge success in challenging domains, such as chess and Go,
where a perfect simulator is available. However, in real-world problems the
dynamics governing the environment are often complex and unknown. In this work
we present the MuZero algorithm which, by combining a tree-based search with a
learned model, achieves superhuman performance in a range of challenging and
visually complex domains, without any knowledge of their underlying dynamics.
MuZero learns a model that, when applied iteratively, predicts the quantities
most directly relevant to planning: the reward, the action-selection policy,
and the value function. When evaluated on 57 different Atari games - the
canonical video game environment for testing AI techniques, in which
model-based planning approaches have historically struggled - our new algorithm
achieved a new state of the art. When evaluated...
more |
pdf
| html
Figures
None.
Tweets
mathena:
Holy Cow this is a good step towards AGI.
https://t.co/LPVSTxu08J
BrundageBot:
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model. Schrittwieser, Antonoglou, Hubert, Simonyan, Sifre, Schmitt, Guez, Lockhart, Hassabis, Graepel, Lillicrap, and Silver https://t.co/gWUdaaVgg5
rosinality:
https://t.co/ymLJ2gITxL 오 이젠 알파고가 아타리도 하네. 모델 기반 RL로의 확장이라 흥미로움.
StatsPapers:
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model. https://t.co/kuLNUldJLn
mooopan:
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model https://t.co/wvd4kKaSpc
😲
KaiLashArul:
RT @mooopan: Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model https://t.co/wvd4kKaSpc
😲
KazuSamejima:
RT @mooopan: Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model https://t.co/wvd4kKaSpc
😲
tak_yamm:
RT @mooopan: Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model https://t.co/wvd4kKaSpc
😲
morioka:
RT @mooopan: Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model https://t.co/wvd4kKaSpc
😲
turkeyfiend:
RT @rosinality: https://t.co/ymLJ2gITxL 오 이젠 알파고가 아타리도 하네. 모델 기반 RL로의 확장이라 흥미로움.
cute_na_piglets:
RT @mooopan: Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model https://t.co/wvd4kKaSpc
😲
ETCShogi:
RT @mooopan: Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model https://t.co/wvd4kKaSpc
😲
ihme_vaeltaa:
RT @mooopan: Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model https://t.co/wvd4kKaSpc
😲
pranjaltandon2:
RT @mooopan: Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model https://t.co/wvd4kKaSpc
😲
THsama2:
RT @mooopan: Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model https://t.co/wvd4kKaSpc
😲
MoTaylor95:
RT @mooopan: Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model https://t.co/wvd4kKaSpc
😲
Github
None.
Youtube
None.
Other stats
Sample Sizes : None.
Authors: 12
Total Words: 0
Unqiue Words: 0
2.299 Mikeys
#4. Retrospective and Prospective Mixture-of-Generators for Task-oriented Dialogue Response Generation
Jiahuan Pei, Pengjie Ren, Christof Monz, Maarten de Rijke
Dialogue response generation (DRG) is a critical component of task-oriented
dialogue systems (TDSs). Its purpose is to generate proper natural language
responses given some context, e.g., historical utterances, system states, etc.
State-of-the-art work focuses on how to better tackle DRG in an end-to-end way.
Typically, such studies assume that each token is drawn from a single
distribution over the output vocabulary, which may not always be optimal.
Responses vary greatly with different intents, e.g., domains, system actions.
We propose a novel mixture-of-generators network (MoGNet) for DRG, where we
assume that each token of a response is drawn from a mixture of distributions.
MoGNet consists of a chair generator and several expert generators. Each expert
is specialized for DRG w.r.t. a particular intent. The chair coordinates
multiple experts and combines the output they have generated to produce more
appropriate responses. We propose two strategies to help the chair make better
decisions, namely, a retrospective...
more |
pdf
| html
Figures
Tweets
SciFi:
Retrospective and Prospective Mixture-of-Generators for Task-oriented Dialogue Response Generation. https://t.co/57kXy0l2XQ
arxiv_cscl:
Retrospective and Prospective Mixture-of-Generators for Task-oriented Dialogue Response Generation https://t.co/mbmKDKcZJp
Github
Source code for end-to-end dialogue model from the MultiWOZ paper (Budzianowski et al. 2018, EMNLP)
Stargazers: 129
Subscribers: 7
Subscribers: 7
Forks: 31
Open Issues: 4
Open Issues: 4
Youtube
None.
Other stats
Sample Sizes : None.
Authors: 4
Total Words: 7028
Unqiue Words: 2223
2.232 Mikeys
#5. Faster AutoAugment: Learning Augmentation Strategies using Backpropagation
Ryuichiro Hataya, Jan Zdenek, Kazuki Yoshizoe, Hideki Nakayama
Data augmentation methods are indispensable heuristics to boost the
performance of deep neural networks, especially in image recognition tasks.
Recently, several studies have shown that augmentation strategies found by
search algorithms outperform hand-made strategies. Such methods employ
black-box search algorithms over image transformations with continuous or
discrete parameters and require a long time to obtain better strategies. In
this paper, we propose a differentiable policy search pipeline for data
augmentation, which is much faster than previous methods. We introduce
approximate gradients for several transformation operations with discrete
parameters as well as the differentiable mechanism for selecting operations. As
the objective of training, we minimize the distance between the distributions
of augmented data and the original data, which can be differentiated. We show
that our method, Faster AutoAugment, achieves significantly faster searching
than prior work without a performance drop.
more |
pdf
| html
Figures
Tweets
yu4u:
👀 https://t.co/je9uFHy3KU https://t.co/r6krqvLlAn
BrundageBot:
Faster AutoAugment: Learning Augmentation Strategies using Backpropagation. Ryuichiro Hataya, Jan Zdenek, Kazuki Yoshizoe, and Hideki Nakayama https://t.co/PgeMC3BfLH
mosko_mule:
Our paper "Faster AutoAugment: Learning Augmentation Strategies using Backpropagation" https://t.co/9UMKK9uvJr is now on arXiv. We approximate gradients of the DA pipeline to enable gradient-based searching. Faster AutoAugment is 20k times faster than the original AutoAugment.
mosko_mule:
IBISでも発表するFaster AutoAugmentがこちらです
https://t.co/9UMKK9uvJr
ブラックボックス最適化を用いる既存手法とは異なり、勾配を近似することでSGDでデータ拡張戦略を学習します。AutoAugmentの2万倍高速です。
ZFPhalanx:
Faster AutoAugment: Learning Augmentation Strategies using Backpropagation
https://t.co/2ExxhTu0wo https://t.co/IYEsWjCi5I
arxivml:
"Faster AutoAugment: Learning Augmentation Strategies using Backpropagation",
Ryuichiro Hataya, Jan Zdenek, Kazuki …
https://t.co/x5hjN6vb3h
arxiv_cscv:
Faster AutoAugment: Learning Augmentation Strategies using Backpropagation https://t.co/NXq3tQd95X
arxiv_cscv:
Faster AutoAugment: Learning Augmentation Strategies using Backpropagation https://t.co/NXq3tPVxHn
kazoo04:
RT @mosko_mule: IBISでも発表するFaster AutoAugmentがこちらです
https://t.co/9UMKK9uvJr
ブラックボックス最適化を用いる既存手法とは異なり、勾配を近似することでSGDでデータ拡張戦略を学習します。AutoAugment…
learn_learning3:
RT @mosko_mule: IBISでも発表するFaster AutoAugmentがこちらです
https://t.co/9UMKK9uvJr
ブラックボックス最適化を用いる既存手法とは異なり、勾配を近似することでSGDでデータ拡張戦略を学習します。AutoAugment…
n_hidekey:
RT @mosko_mule: IBISでも発表するFaster AutoAugmentがこちらです
https://t.co/9UMKK9uvJr
ブラックボックス最適化を用いる既存手法とは異なり、勾配を近似することでSGDでデータ拡張戦略を学習します。AutoAugment…
jaguring1:
RT @mosko_mule: IBISでも発表するFaster AutoAugmentがこちらです
https://t.co/9UMKK9uvJr
ブラックボックス最適化を用いる既存手法とは異なり、勾配を近似することでSGDでデータ拡張戦略を学習します。AutoAugment…
hayashiyus:
RT @mosko_mule: Our paper "Faster AutoAugment: Learning Augmentation Strategies using Backpropagation" https://t.co/9UMKK9uvJr is now on ar…
hayashiyus:
RT @mosko_mule: IBISでも発表するFaster AutoAugmentがこちらです
https://t.co/9UMKK9uvJr
ブラックボックス最適化を用いる既存手法とは異なり、勾配を近似することでSGDでデータ拡張戦略を学習します。AutoAugment…
HirokatuKataoka:
RT @mosko_mule: Our paper "Faster AutoAugment: Learning Augmentation Strategies using Backpropagation" https://t.co/9UMKK9uvJr is now on ar…
mosko_mule:
RT @mosko_mule: IBISでも発表するFaster AutoAugmentがこちらです
https://t.co/9UMKK9uvJr
ブラックボックス最適化を用いる既存手法とは異なり、勾配を近似することでSGDでデータ拡張戦略を学習します。AutoAugment…
mosko_mule:
RT @mosko_mule: Our paper "Faster AutoAugment: Learning Augmentation Strategies using Backpropagation" https://t.co/9UMKK9uvJr is now on ar…
mosko_mule:
RT @mosko_mule: Our paper "Faster AutoAugment: Learning Augmentation Strategies using Backpropagation" https://t.co/9UMKK9uvJr is now on ar…
mosko_mule:
RT @mosko_mule: IBISでも発表するFaster AutoAugmentがこちらです
https://t.co/9UMKK9uvJr
ブラックボックス最適化を用いる既存手法とは異なり、勾配を近似することでSGDでデータ拡張戦略を学習します。AutoAugment…
imenurok:
RT @mosko_mule: IBISでも発表するFaster AutoAugmentがこちらです
https://t.co/9UMKK9uvJr
ブラックボックス最適化を用いる既存手法とは異なり、勾配を近似することでSGDでデータ拡張戦略を学習します。AutoAugment…
shunk031:
RT @mosko_mule: IBISでも発表するFaster AutoAugmentがこちらです
https://t.co/9UMKK9uvJr
ブラックボックス最適化を用いる既存手法とは異なり、勾配を近似することでSGDでデータ拡張戦略を学習します。AutoAugment…
jaialkdanel:
RT @mosko_mule: IBISでも発表するFaster AutoAugmentがこちらです
https://t.co/9UMKK9uvJr
ブラックボックス最適化を用いる既存手法とは異なり、勾配を近似することでSGDでデータ拡張戦略を学習します。AutoAugment…
Scaled_Wurm:
RT @mosko_mule: IBISでも発表するFaster AutoAugmentがこちらです
https://t.co/9UMKK9uvJr
ブラックボックス最適化を用いる既存手法とは異なり、勾配を近似することでSGDでデータ拡張戦略を学習します。AutoAugment…
udmrzn:
RT @arxiv_cscv: Faster AutoAugment: Learning Augmentation Strategies using Backpropagation https://t.co/NXq3tQd95X
kibo35:
RT @mosko_mule: IBISでも発表するFaster AutoAugmentがこちらです
https://t.co/9UMKK9uvJr
ブラックボックス最適化を用いる既存手法とは異なり、勾配を近似することでSGDでデータ拡張戦略を学習します。AutoAugment…
hrs1985:
RT @mosko_mule: IBISでも発表するFaster AutoAugmentがこちらです
https://t.co/9UMKK9uvJr
ブラックボックス最適化を用いる既存手法とは異なり、勾配を近似することでSGDでデータ拡張戦略を学習します。AutoAugment…
jd_mashiro:
RT @mosko_mule: Our paper "Faster AutoAugment: Learning Augmentation Strategies using Backpropagation" https://t.co/9UMKK9uvJr is now on ar…
momiji_fullmoon:
RT @mosko_mule: IBISでも発表するFaster AutoAugmentがこちらです
https://t.co/9UMKK9uvJr
ブラックボックス最適化を用いる既存手法とは異なり、勾配を近似することでSGDでデータ拡張戦略を学習します。AutoAugment…
matsui_kota:
RT @mosko_mule: Our paper "Faster AutoAugment: Learning Augmentation Strategies using Backpropagation" https://t.co/9UMKK9uvJr is now on ar…
matsui_kota:
RT @mosko_mule: IBISでも発表するFaster AutoAugmentがこちらです
https://t.co/9UMKK9uvJr
ブラックボックス最適化を用いる既存手法とは異なり、勾配を近似することでSGDでデータ拡張戦略を学習します。AutoAugment…
toorun12:
RT @mosko_mule: IBISでも発表するFaster AutoAugmentがこちらです
https://t.co/9UMKK9uvJr
ブラックボックス最適化を用いる既存手法とは異なり、勾配を近似することでSGDでデータ拡張戦略を学習します。AutoAugment…
StaPriEG2:
RT @mosko_mule: IBISでも発表するFaster AutoAugmentがこちらです
https://t.co/9UMKK9uvJr
ブラックボックス最適化を用いる既存手法とは異なり、勾配を近似することでSGDでデータ拡張戦略を学習します。AutoAugment…
morioka:
RT @mosko_mule: IBISでも発表するFaster AutoAugmentがこちらです
https://t.co/9UMKK9uvJr
ブラックボックス最適化を用いる既存手法とは異なり、勾配を近似することでSGDでデータ拡張戦略を学習します。AutoAugment…
doiken23:
RT @mosko_mule: IBISでも発表するFaster AutoAugmentがこちらです
https://t.co/9UMKK9uvJr
ブラックボックス最適化を用いる既存手法とは異なり、勾配を近似することでSGDでデータ拡張戦略を学習します。AutoAugment…
morioka:
RT @mosko_mule: Our paper "Faster AutoAugment: Learning Augmentation Strategies using Backpropagation" https://t.co/9UMKK9uvJr is now on ar…
muktabh:
RT @arxiv_cscv: Faster AutoAugment: Learning Augmentation Strategies using Backpropagation https://t.co/NXq3tQd95X
muktabh:
RT @arxiv_cscv: Faster AutoAugment: Learning Augmentation Strategies using Backpropagation https://t.co/NXq3tPVxHn
_naoto_inoue:
RT @mosko_mule: IBISでも発表するFaster AutoAugmentがこちらです
https://t.co/9UMKK9uvJr
ブラックボックス最適化を用いる既存手法とは異なり、勾配を近似することでSGDでデータ拡張戦略を学習します。AutoAugment…
_naoto_inoue:
RT @mosko_mule: Our paper "Faster AutoAugment: Learning Augmentation Strategies using Backpropagation" https://t.co/9UMKK9uvJr is now on ar…
ssky_ryo:
RT @yu4u: 👀 https://t.co/je9uFHy3KU https://t.co/r6krqvLlAn
SythonUK:
RT @mosko_mule: IBISでも発表するFaster AutoAugmentがこちらです
https://t.co/9UMKK9uvJr
ブラックボックス最適化を用いる既存手法とは異なり、勾配を近似することでSGDでデータ拡張戦略を学習します。AutoAugment…
kud_wata:
RT @mosko_mule: IBISでも発表するFaster AutoAugmentがこちらです
https://t.co/9UMKK9uvJr
ブラックボックス最適化を用いる既存手法とは異なり、勾配を近似することでSGDでデータ拡張戦略を学習します。AutoAugment…
Eseshinpu:
RT @mosko_mule: IBISでも発表するFaster AutoAugmentがこちらです
https://t.co/9UMKK9uvJr
ブラックボックス最適化を用いる既存手法とは異なり、勾配を近似することでSGDでデータ拡張戦略を学習します。AutoAugment…
FBWM8888:
RT @mosko_mule: IBISでも発表するFaster AutoAugmentがこちらです
https://t.co/9UMKK9uvJr
ブラックボックス最適化を用いる既存手法とは異なり、勾配を近似することでSGDでデータ拡張戦略を学習します。AutoAugment…
eve_yk:
RT @mosko_mule: IBISでも発表するFaster AutoAugmentがこちらです
https://t.co/9UMKK9uvJr
ブラックボックス最適化を用いる既存手法とは異なり、勾配を近似することでSGDでデータ拡張戦略を学習します。AutoAugment…
harujoh:
RT @mosko_mule: IBISでも発表するFaster AutoAugmentがこちらです
https://t.co/9UMKK9uvJr
ブラックボックス最適化を用いる既存手法とは異なり、勾配を近似することでSGDでデータ拡張戦略を学習します。AutoAugment…
63556poiuytrewq:
RT @mosko_mule: IBISでも発表するFaster AutoAugmentがこちらです
https://t.co/9UMKK9uvJr
ブラックボックス最適化を用いる既存手法とは異なり、勾配を近似することでSGDでデータ拡張戦略を学習します。AutoAugment…
chachay:
RT @mosko_mule: IBISでも発表するFaster AutoAugmentがこちらです
https://t.co/9UMKK9uvJr
ブラックボックス最適化を用いる既存手法とは異なり、勾配を近似することでSGDでデータ拡張戦略を学習します。AutoAugment…
ponpokoz:
RT @mosko_mule: IBISでも発表するFaster AutoAugmentがこちらです
https://t.co/9UMKK9uvJr
ブラックボックス最適化を用いる既存手法とは異なり、勾配を近似することでSGDでデータ拡張戦略を学習します。AutoAugment…
ko_ash:
RT @mosko_mule: IBISでも発表するFaster AutoAugmentがこちらです
https://t.co/9UMKK9uvJr
ブラックボックス最適化を用いる既存手法とは異なり、勾配を近似することでSGDでデータ拡張戦略を学習します。AutoAugment…
hengcherkeng:
RT @ZFPhalanx: Faster AutoAugment: Learning Augmentation Strategies using Backpropagation
https://t.co/2ExxhTu0wo https://t.co/IYEsWjCi5I
f16xl:
RT @mosko_mule: IBISでも発表するFaster AutoAugmentがこちらです
https://t.co/9UMKK9uvJr
ブラックボックス最適化を用いる既存手法とは異なり、勾配を近似することでSGDでデータ拡張戦略を学習します。AutoAugment…
nskm_m:
RT @mosko_mule: IBISでも発表するFaster AutoAugmentがこちらです
https://t.co/9UMKK9uvJr
ブラックボックス最適化を用いる既存手法とは異なり、勾配を近似することでSGDでデータ拡張戦略を学習します。AutoAugment…
nightwalker:
RT @mosko_mule: IBISでも発表するFaster AutoAugmentがこちらです
https://t.co/9UMKK9uvJr
ブラックボックス最適化を用いる既存手法とは異なり、勾配を近似することでSGDでデータ拡張戦略を学習します。AutoAugment…
toto_toilet:
RT @mosko_mule: IBISでも発表するFaster AutoAugmentがこちらです
https://t.co/9UMKK9uvJr
ブラックボックス最適化を用いる既存手法とは異なり、勾配を近似することでSGDでデータ拡張戦略を学習します。AutoAugment…
ashi__no:
RT @mosko_mule: IBISでも発表するFaster AutoAugmentがこちらです
https://t.co/9UMKK9uvJr
ブラックボックス最適化を用いる既存手法とは異なり、勾配を近似することでSGDでデータ拡張戦略を学習します。AutoAugment…
MatsElctrcBlu:
RT @mosko_mule: IBISでも発表するFaster AutoAugmentがこちらです
https://t.co/9UMKK9uvJr
ブラックボックス最適化を用いる既存手法とは異なり、勾配を近似することでSGDでデータ拡張戦略を学習します。AutoAugment…
MktO740123:
RT @mosko_mule: Our paper "Faster AutoAugment: Learning Augmentation Strategies using Backpropagation" https://t.co/9UMKK9uvJr is now on ar…
MktO740123:
RT @mosko_mule: IBISでも発表するFaster AutoAugmentがこちらです
https://t.co/9UMKK9uvJr
ブラックボックス最適化を用いる既存手法とは異なり、勾配を近似することでSGDでデータ拡張戦略を学習します。AutoAugment…
kuz44ma69:
RT @arxiv_cscv: Faster AutoAugment: Learning Augmentation Strategies using Backpropagation https://t.co/NXq3tPVxHn
MassBassLol:
RT @ZFPhalanx: Faster AutoAugment: Learning Augmentation Strategies using Backpropagation
https://t.co/2ExxhTu0wo https://t.co/IYEsWjCi5I
Github
None.
Youtube
None.
Other stats
Sample Sizes : None.
Authors: 4
Total Words: 5665
Unqiue Words: 1807
2.197 Mikeys
#6. A note on the number of irrational odd zeta values
Li Lai, Pin Yu
By modifying the auxiliary rational functions of Fischler, Sprang and Zudilin
in \cite{FSZ2019}, we prove that, for all odd integer $s \geq 10^4$, there are
at least $\frac{1}{10}\frac{s^{1/2}}{(\log s)^{1/2}}$ irrational numbers among
the following odd zeta values: $\zeta(3),\zeta(5),\zeta(7),\cdots,\zeta(s)$.
This improves the lower bound $2^{(1-\varepsilon)\frac{\log s}{\log\log s}}$ in
\cite{FSZ2019}.
more |
pdf
| html
Figures
None.
Tweets
tyamada1093:
https://t.co/HU0FChkA1o
ζ関数の奇数での値の無理数性に新たな結果。
s が10000より大きい奇数のとき ζ(n), n=3, 5,...,s のうち少なくとも (s/log s)^{1/2}/10 個は無理数。
mathNTb:
Li Lai, Pin Yu : A note on the number of irrational odd zeta values https://t.co/2N6mNSaoQb https://t.co/myOztkcIzs
adhara_mathphys:
RT @tyamada1093: https://t.co/HU0FChkA1o
ζ関数の奇数での値の無理数性に新たな結果。
s が10000より大きい奇数のとき ζ(n), n=3, 5,...,s のうち少なくとも (s/log s)^{1/2}/10 個は無理数。
691_7758337633:
RT @tyamada1093: https://t.co/HU0FChkA1o
ζ関数の奇数での値の無理数性に新たな結果。
s が10000より大きい奇数のとき ζ(n), n=3, 5,...,s のうち少なくとも (s/log s)^{1/2}/10 個は無理数。
691_7758337633:
RT @mathNTb: Li Lai, Pin Yu : A note on the number of irrational odd zeta values https://t.co/2N6mNSaoQb https://t.co/myOztkcIzs
suugaku_arai:
RT @tyamada1093: https://t.co/HU0FChkA1o
ζ関数の奇数での値の無理数性に新たな結果。
s が10000より大きい奇数のとき ζ(n), n=3, 5,...,s のうち少なくとも (s/log s)^{1/2}/10 個は無理数。
sugar_underkey:
RT @tyamada1093: https://t.co/HU0FChkA1o
ζ関数の奇数での値の無理数性に新たな結果。
s が10000より大きい奇数のとき ζ(n), n=3, 5,...,s のうち少なくとも (s/log s)^{1/2}/10 個は無理数。
akira_chem:
RT @tyamada1093: https://t.co/HU0FChkA1o
ζ関数の奇数での値の無理数性に新たな結果。
s が10000より大きい奇数のとき ζ(n), n=3, 5,...,s のうち少なくとも (s/log s)^{1/2}/10 個は無理数。
Lbfuvab:
RT @tyamada1093: https://t.co/HU0FChkA1o
ζ関数の奇数での値の無理数性に新たな結果。
s が10000より大きい奇数のとき ζ(n), n=3, 5,...,s のうち少なくとも (s/log s)^{1/2}/10 個は無理数。
chibafx:
RT @tyamada1093: https://t.co/HU0FChkA1o
ζ関数の奇数での値の無理数性に新たな結果。
s が10000より大きい奇数のとき ζ(n), n=3, 5,...,s のうち少なくとも (s/log s)^{1/2}/10 個は無理数。
Github
None.
Youtube
None.
Other stats
Sample Sizes : None.
Authors: 2
Total Words: 0
Unqiue Words: 0
2.188 Mikeys
#7. Non-linear effects in early Universe cosmology
Pedro Carrilho
In this thesis, we discuss several instances in which non-linear behaviour
affects cosmological evolution in the early Universe. We begin by reviewing the
standard cosmological model and the tools used to understand it theoretically
and to compute its observational consequences. This includes a detailed
exposition of cosmological perturbation theory and the theory of inflation. We
then describe the results in this thesis, starting with the non-linear
evolution of the curvature perturbation in the presence of vector and tensor
fluctuations, in which we identify the version of that variable that is
conserved in the most general situation. Next, we use second order perturbation
theory to describe the most general initial conditions for the evolution of
scalar perturbations at second order in the standard cosmological model. We
compute approximate solutions valid in the initial stages of the evolution,
which can be used to initialize second order Boltzmann codes, and to compute
many observables taking isocurvature modes into account....
more |
pdf
| html
Figures
Tweets
OSablin:
"Non-linear effects in early Universe cosmology. (arXiv:1911.08313v1 [gr-qc])" https://t.co/EldV4uNnMg
RelativityPaper:
Non-linear effects in early Universe cosmology. https://t.co/dGfXtFbrGf
Github
A Python Package for the calculation of inflationary correlation functions.
Stargazers: 8
Subscribers: 3
Subscribers: 3
Forks: 3
Open Issues: 4
Open Issues: 4
Youtube
None.
Other stats
Sample Sizes : None.
Authors: 1
Total Words: 76804
Unqiue Words: 9565
2.173 Mikeys
#8. Live Face De-Identification in Video
Oran Gafni, Lior Wolf, Yaniv Taigman
We propose a method for face de-identification that enables fully automatic
video modification at high frame rates. The goal is to maximally decorrelate
the identity, while having the perception (pose, illumination and expression)
fixed. We achieve this by a novel feed-forward encoder-decoder network
architecture that is conditioned on the high-level representation of a person's
facial image. The network is global, in the sense that it does not need to be
retrained for a given video or for a given identity, and it creates natural
looking image sequences with little distortion in time.
more |
pdf
| html
Figures
None.
Tweets
BrundageBot:
Live Face De-Identification in Video. Oran Gafni, Lior Wolf, and Yaniv Taigman https://t.co/qw6TrNRa3s
roadrunning01:
Live Face De-Identification in Video
pdf: https://t.co/rOW3Df0Fxm
abs: https://t.co/Y1f3j5vTdp
video: https://t.co/lUY5y0OA0w https://t.co/HQJ5yibeiI
StatsPapers:
Live Face De-Identification in Video. https://t.co/8UPhikRg2O
arxiv_csgr:
Live Face De-Identification in Video https://t.co/H69Qn2CCLk
arxiv_csgr:
Live Face De-Identification in Video https://t.co/H69Qn2Ue9U
hey_kishore:
RT @roadrunning01: Live Face De-Identification in Video
pdf: https://t.co/rOW3Df0Fxm
abs: https://t.co/Y1f3j5vTdp
video: https://t.co/lUY5y…
MassBassLol:
RT @roadrunning01: Live Face De-Identification in Video
pdf: https://t.co/rOW3Df0Fxm
abs: https://t.co/Y1f3j5vTdp
video: https://t.co/lUY5y…
Github
None.
Youtube
None.
Other stats
Sample Sizes : None.
Authors: 3
Total Words: 0
Unqiue Words: 0
2.163 Mikeys
#9. HighEr-Resolution Network for Image Demosaicing and Enhancing
Kangfu Mei, Juncheng Li, Jiajie Zhang, Haoyu Wu, Jie Li, Rui Huang
Neural-networks based image restoration methods tend to use low-resolution
image patches for training. Although higher-resolution image patches can
provide more global information, state-of-the-art methods cannot utilize them
due to their huge GPU memory usage, as well as the instable training process.
However, plenty of studies have shown that global information is crucial for
image restoration tasks like image demosaicing and enhancing. In this work, we
propose a HighEr-Resolution Network (HERN) to fully learning global information
in high-resolution image patches. To achieve this, the HERN employs two
parallel paths to learn image features in two different resolutions,
respectively. By combining global-aware features and multi-scale features, our
HERN is able to learn global information with feasible GPU memory usage.
Besides, we introduce a progressive training method to solve the instability
issue and accelerate model convergence. On the task of image demosaicing and
enhancing, our HERN achieves state-of-the-art performance...
more |
pdf
| html
Figures
Tweets
BrundageBot:
HighEr-Resolution Network for Image Demosaicing and Enhancing. Kangfu Mei, Juncheng Li, Jiajie Zhang, Haoyu Wu, Jie Li, and Rui Huang https://t.co/gZ5SoLGnEl
arxiv_cscv:
HighEr-Resolution Network for Image Demosaicing and Enhancing https://t.co/JDabMM1ehW
Github
Winning solution in AIM 2019 RAW to RGB Mapping Challenge (ICCV2019W)
Stargazers: 5
Subscribers: 1
Subscribers: 1
Forks: 1
Open Issues: 0
Open Issues: 0
Youtube
None.
Other stats
Sample Sizes : None.
Authors: 6
Total Words: 4612
Unqiue Words: 1450
2.156 Mikeys
#10. Extended Answer and Uncertainty Aware Neural Question Generation
Hongwei Zeng, Zhuo Zhi, Jun Liu, Bifan Wei
In this paper, we study automatic question generation, the task of creating
questions from corresponding text passages where some certain spans of the text
can serve as the answers. We propose an Extended Answer-aware Network (EAN)
which is trained with Word-based Coverage Mechanism (WCM) and decodes with
Uncertainty-aware Beam Search (UBS). The EAN represents the target answer by
its surrounding sentence with an encoder, and incorporates the information of
the extended answer into paragraph representation with gated
paragraph-to-answer attention to tackle the problem of the inadequate
representation of the target answer. To reduce undesirable repetition, the WCM
penalizes repeatedly attending to the same words at different time-steps in the
training stage. The UBS aims to seek a better balance between the model
confidence in copying words from an input text paragraph and the confidence in
generating words from a vocabulary. We conduct experiments on the SQuAD
dataset, and the results show our approach achieves significant...
more |
pdf
| html
Figures
None.
Tweets
BrundageBot:
Extended Answer and Uncertainty Aware Neural Question Generation. Hongwei Zeng, Zhuo Zhi, Jun Liu, and Bifan Wei https://t.co/DyoNZSgtVR
SciFi:
Extended Answer and Uncertainty Aware Neural Question Generation. https://t.co/HRZBETc3wp
arxiv_cscl:
Extended Answer and Uncertainty Aware Neural Question Generation https://t.co/1Ims5kfElt
arxiv_cscl:
Extended Answer and Uncertainty Aware Neural Question Generation https://t.co/1Ims5kfElt
arxiv_cscl:
Extended Answer and Uncertainty Aware Neural Question Generation https://t.co/1Ims5jY2WT
Github
None.
Youtube
None.
Other stats
Sample Sizes : None.
Authors: 4
Total Words: 0
Unqiue Words: 0
About
Assert is a website where the best academic papers on arXiv (computer science, math, physics), bioRxiv (biology), BITSS (reproducibility), EarthArXiv (earth science), engrXiv (engineering), LawArXiv (law), PsyArXiv (psychology), SocArXiv (social science), and SportRxiv (sport research) bubble to the top each day.
Papers are scored (in real-time) based on how verifiable they are (as determined by their Github repos) and how interesting they are (based on Twitter).
To see top papers, follow us on twitter @assertpub_ (arXiv), @assert_pub (bioRxiv), and @assertpub_dev (everything else).
To see beautiful figures extracted from papers, follow us on Instagram.
Tracking 225,391 papers.
Search
Sort results based on if they are interesting or reproducible.
Interesting
Reproducible