Deep Residual Learning for Image Recognition
ResNet, an image-recognition network, uses shortcuts between layers to make much deeper networks easier to train.
Selected research papers and books, linked to their authors.
ResNet, an image-recognition network, uses shortcuts between layers to make much deeper networks easier to train.
AlexNet sharply improved image recognition with a deep neural network.
VGG networks improved image recognition by stacking more layers.
U-Net outlines cells and other structures in biomedical images.
Shared neural-network processing made locating and identifying objects faster with Faster R-CNN.
The Vision Transformer recognizes images by treating patches like words in a sequence.
A large labeled image collection for training and testing object-recognition systems.
Showed how neural networks could learn to read handwritten characters for document processing.
YOLO locates and identifies objects in a single network pass for real-time detection.
A dataset of everyday scenes with individual objects labeled and outlined.