Concept
Convolutional Neural Networks
Layered convolutional filters that learn spatial feature hierarchies — the backbone of modern computer vision.
Papers
-
Deep Residual Learning for Image Recognition
Residual learning let networks go hundreds of layers deep by having layers fit a residual rather than a full mapping, solving the degradation problem. Residual connections are now standard in nearly every deep architecture, Transformers included.
arxiv.org ↗ -
ImageNet Classification with Deep Convolutional Neural Networks
The deep-learning breakthrough on ImageNet: a large GPU-trained convolutional network cut top-5 error nearly in half and touched off the modern era of deep learning in vision.
proceedings.neurips.cc ↗