Halo! Saya Valentin Khrulkov, peneliti dari tim Riset Yandex. Kami secara teratur menghadiri konferensi industri, dan kemudian berbagi kesan kami tentang Habré: pembicara mana yang diingat, mana yang tidak dapat diabaikan, poster siapa yang paling menarik perhatian. 2020 membuat penyesuaian signifikan terhadap jadwal biasa: banyak acara dibatalkan dan dijadwal ulang, tetapi penyelenggara beberapa di antaranya mempertaruhkan mencoba format baru.
CVPR 2020 adalah 7600 peserta, 5025 karya, acara dan interaksi, 1.497.800 menit diskusi - dan semuanya online. Detail lebih lanjut ada di bawah potongan.
Bagaimana itu: rencana vs kenyataan
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) : .
NLP 2017 , . , — , — : «-»? : — , — , .
Yandex Research , : ? : . , , : 10%. — .
, CVPR 2020 - . , , .