A Generic Visualization Approach for Convolutional Neural Networks

by   Ahmed Taha, et al.

Retrieval networks are essential for searching and indexing. Compared to classification networks, attention visualization for retrieval networks is hardly studied. We formulate attention visualization as a constrained optimization problem. We leverage the unit L2-Norm constraint as an attention filter (L2-CAF) to localize attention in both classification and retrieval networks. Unlike recent literature, our approach requires neither architectural changes nor fine-tuning. Thus, a pre-trained network's performance is never undermined L2-CAF is quantitatively evaluated using weakly supervised object localization. State-of-the-art results are achieved on classification networks. For retrieval networks, significant improvement margins are achieved over a Grad-CAM baseline. Qualitative evaluation demonstrates how the L2-CAF visualizes attention per frame for a recurrent retrieval network. Further ablation studies highlight the computational cost of our approach and compare L2-CAF with other feasible alternatives. Code available at https://bit.ly/3iDBLFv


page 10

page 12

page 13

page 22


ViTOL: Vision Transformer for Weakly Supervised Object Localization

Weakly supervised object localization (WSOL) aims at predicting object l...

Self-Transfer Learning for Fully Weakly Supervised Object Localization

Recent advances of deep learning have achieved remarkable performances i...

Channel Recurrent Attention Networks for Video Pedestrian Retrieval

Full attention, which generates an attention value per element of the in...

SVMax: A Feature Embedding Regularizer

A neural network regularizer (e.g., weight decay) boosts performance by ...

Dual-Path Convolutional Image-Text Embedding

This paper considers the task of matching images and sentences. The chal...

Retrieval Augmented Classification for Long-Tail Visual Recognition

We introduce Retrieval Augmented Classification (RAC), a generic approac...

Code Repositories


(ECCV2020) Tensorflow implementation of A Generic Visualization Approach for Convolutional Neural Networks

view repo


(ECCV2020) PyTorch implementation of A Generic Visualization Approach for Convolutional Neural Networks

view repo