An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale (Paper Explained)

Описание: #ai #research #transformers

Transformers are Ruining Convolutions. This paper, under review at ICLR, shows that given enough data, a standard Transformer can outperform Convolutional Neural Networks in image recognition tasks, which are classically tasks where CNNs excel. In this Video, I explain the architecture of the Vision Transformer (ViT), the reason why it works better and rant about why double-bline peer review is broken.

OUTLINE:
0:00 - Introduction
0:30 - Double-Blind Review is Broken
5:20 - Overview
6:55 - Transformers for Images
10:40 - Vision Transformer Architecture
16:30 - Experimental Results
18:45 - What does the Model Learn?
21:00 - Why Transformers are Ruining Everything
27:45 - Inductive Biases in Transformers
29:05 - Conclusion & Comments

Paper (Under Review): https://openreview.net/forum?id=YicbF...
Arxiv version: https://arxiv.org/abs/2010.11929

BiT Paper: https://arxiv.org/pdf/1912.11370.pdf
ImageNet-ReaL Paper: https://arxiv.org/abs/2006.07159

My Video on BiT (Big Transfer):    • Big Transfer (BiT): General Visual Represe...  
My Video on Transformers:    • Attention Is All You Need  
My Video on BERT:    • BERT: Pre-training of Deep Bidirectional T...  
My Video on ResNets:    • [Classic] Deep Residual Learning for Image...  


Abstract: While the Transformer architecture has become the de-facto standard for natural language processing tasks, its applications to computer vision remain limited. In vision, attention is either applied in conjunction with convolutional networks, or used to replace certain components of convolutional networks while keeping their overall structure in place. We show that this reliance on CNNs is not necessary and a pure transformer can perform very well on image classification tasks when applied directly to sequences of image patches. When pre-trained on large amounts of data and transferred to multiple recognition benchmarks (ImageNet, CIFAR-100, VTAB, etc), Vision Transformer attains excellent results compared to state-of-the-art convolutional networks while requiring substantially fewer computational resources to train.

Authors: Anonymous / Under Review

Errata:
Patches are not flattened, but vectorized

Links:
YouTube:    / yannickilcher  
Twitter:   / ykilcher  
Discord:   / discord  
BitChute: https://www.bitchute.com/channel/yann...
Minds: https://www.minds.com/ykilcher
Parler: https://parler.com/profile/YannicKilcher
LinkedIn:   / yannic-kilcher-488534136  

If you want to support me, the best thing to do is to share out the content :)

If you want to support me financially (completely optional and voluntary, but a lot of people have asked for this):
SubscribeStar: https://www.subscribestar.com/yannick...
Patreon:   / yannickilcher  
Bitcoin (BTC): bc1q49lsw3q325tr58ygf8sudx2dqfguclvngvy2cq
Ethereum (ETH): 0x7ad3513E3B8f66799f507Aa7874b1B0eBC7F85e2
Litecoin (LTC): LQW2TRyKYetVC8WjFkhpPhtpbDM4Vw7r9m
Monero (XMR): 4ACL8AGrEo5hAir8A9CeVrW8pEauWvnp1WnSDZxW7tziCDLhZAGsgzhRQABDnFy8yuM9fWJDviJPHKRjV4FWt19CJZN9D4n