O que vamos lembrar CVPR 2020. Como a conferência sobre visão computacional evoluiu online

Olá! Sou Valentin Khrulkov, pesquisador da equipe de Pesquisa Yandex. Frequentamos regularmente conferências do setor e depois compartilhamos nossas impressões sobre Habré: qual dos palestrantes foi lembrado, quais estandes não podiam ser ignorados, cujos pôsteres chamaram mais atenção. 2020 fez ajustes significativos na programação usual: muitos eventos foram cancelados e remarcados, mas os organizadores de alguns deles arriscaram tentar novos formatos.

O CVPR 2020 tem 7600 participantes, 5025 trabalhos, eventos e interações, 1.497.800 minutos de discussões - e tudo online. Mais detalhes estão sob o corte.

Como era: planos x realidade

Conference on Computer Vision and Pattern Recognition — — . : , — , «». CPRV — A, A1 A* — , ICCV ECCV. : 20% . — : , . — 25% . 6656 , — 1470, — 335. — , , . -.

: — , — , , — Zoom. , , , - -. , , . , :

-: 350–500$. , ICLR, , 100$.
. : - - .
: , , , .
: . , 12 : , . . , .

: .
: .
.
: .
.

cvpr20.com:

: VS

: — , — . : , , ?

, , -: , . - : ? — . Zoom, .

Efficient Data Annotation for Self-Driving Cars via Crowdsourcing on a Large-Scale , 70 — - , - . ( , , , ). : . , , : , .

- , , — - , - , . , , .

, . , . , : 2D- () 3D- ( , ). , SD , . : , .

, , . — , 100 ( , ). — 30 000 , . : , «» — , . :

! , . Kitware, IBM Cornell, , .

Cross-Batch Memory for Embedding Learning:

: , . - GPU : .

: , , , , , / . ( ) .

CNN-generated images are surprisingly easy to spot… for now:

( GAN’) , : . , state-of-the-art GAN’, , .

: , . , , GAN, , .

Learning Better Lossless Compression Using Lossy Compression: ,

(lossless). : state-of-the-art (lossy), lossless .

, lossless . , CVPR , , , lossless-JPEG2000 WebP.

Image Processing Using Multi-Code GAN Prior:

, GAN , , ? , ?

, : , , Prior GAN — , , .

Effectively Unbiased FID and Inception Score and where to find them: GANs

FID . , .

, . , , , , .

FDA: Fourier Domain Adaptation for Semantic Segmentation:

domain adaptation: - - . , /. .

Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline:

HDR (High Dynamic Range) LDR (Low Dynamic Range) : , , . LDR-HDR . : state-of-the-art, , .

A Multigrid Method for Efficiently Training Video Models: tradeoff

, , : , . , .

, : , , , . ( «», ). : 4,5 .

Towards Robust Image Classification Using Sequential Attention Models:

DeepMind ( CNN, LSTM ) — ( ) () . :

Feedforward : , .
«» : . , .

LSTM, ResNet': , — , — .

150 TPU , , . , «» , - .

Adversarial Vertex Mixup: Toward Better Adversarially Robust Generalization:

. generalization gap adversarial training ( 40%). :

Mixup — .
Label smoothing — - one-hot target, u: — u, (1 — u) .

. x x* ( PGD ), «adversarial vertex kx*», , x. , mixup (x kx*).

— ( ) (, , ).

, — SOTA — , PGD .

High-Resolution Daytime Translation Without Domain Labels:

, , ? , . , unsupervised .

: AdaIN , (style transfer) skip-connections, . , (1024 x 1024) : .

Hyperbolic Image Embeddings:

NLP 2017 , . , — , — : «-»? : — , — , .

Yandex Research , : ? : . , , : 10%. — .

, CVPR 2020 - . , , .

, , , , — , . , . !

All Articles