A Generic Visualization Approach for Convolutional Neural Networks

07/19/2020
by   Ahmed Taha, et al.
59

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

READ FULL TEXT

page 10

page 12

page 13

page 22

04/14/2022

ViTOL: Vision Transformer for Weakly Supervised Object Localization

Weakly supervised object localization (WSOL) aims at predicting object l...
02/04/2016

Self-Transfer Learning for Fully Weakly Supervised Object Localization

Recent advances of deep learning have achieved remarkable performances i...
10/07/2020

Channel Recurrent Attention Networks for Video Pedestrian Retrieval

Full attention, which generates an attention value per element of the in...
03/04/2021

SVMax: A Feature Embedding Regularizer

A neural network regularizer (e.g., weight decay) boosts performance by ...
11/15/2017

Dual-Path Convolutional Image-Text Embedding

This paper considers the task of matching images and sentences. The chal...
02/22/2022

Retrieval Augmented Classification for Long-Tail Visual Recognition

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

Code Repositories

constrained_attention_filter

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


view repo

l2_caf_pytorch

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


view repo