2021
CVPR
CVPR 2021
Differentiable Patch Selection for Image Recognition
Abstract
Neural Networks require large amounts of memory and compute to process high resolution images, even when only a small part of the image is actually informative for the task at hand. We propose a method based on a differentiable Top-K operator to select the most relevant parts of the input to efficiently process high resolution images. Our method may be interfaced with any downstream neural network, is able to aggregate information from different patches in a flexible way, and allows the whole model to be trained end-to-end using backpropagation. We show results for traffic sign recognition, inter-patch relationship reasoning, and fine-grained recognition without using object/part bounding box annotations during training.
🌉
Interdisciplinary Bridge
— Computer Vision and Deep Learning and Machine Learning
🧭
Keyword Pioneer
— differentiable patch selection
🐝
Cross-Pollinator
— Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio
Authors
Topics
Machine Learning > Application Areas > Efficient Computing
Deep Learning > Techniques > Model Architecture
Machine Learning > Learning Types > Representation Learning
Deep Learning > Learning Types > Self-Supervised Learning
Deep Learning > Learning Types > Deep Learning
Computer Vision > Core AI > Computer Vision
Deep Learning > Techniques > Attention