| paper | topic | task | util | published |
|---|---|---|---|---|
| Is Attention Better Than Matrix Decomposition? | attention alternative | seg/GAN | review | ICLR (under review) |
| Learning with feature dependent label noise: a progressive approach | noisy label | class- | review | ICLR (under review) |
| An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale | tranformer is the best | class++ | review | ICLR (under review) |
| Mind the Pad -- CNNs Can Develop Blind Spots | flaw in padding | det | review | ICLR (under review) |
- classification
- class- = cifar
- class = imagenet
- class++ = JFT300M