Attention Branch Network: Learning of Attention Mechanism for Visual Explanation

12/25/2018
by   Hiroshi Fukui, et al.
24

Visual explanation enables human to understand the decision making of Deep Convolutional Neural Network (CNN), but it is insufficient to contribute the performance improvement. In this paper, we focus on the attention map for visual explanation, which represents high response value as the important region in image recognition. This region significantly improves the performance of CNN by introducing an attention mechanism that focuses on a specific region in an image. In this work, we propose Attention Branch Network (ABN), which extends the top-down visual explanation model by introducing a branch structure with an attention mechanism. ABN can be applicable to several image recognition tasks by introducing a branch for attention mechanism and is trainable for the visual explanation and image recognition in end-to-end manner. We evaluate ABN on several image recognition tasks such as image classification, fine-grained recognition, and multiple facial attributes recognition. Experimental results show that ABN can outperform the accuracy of baseline models on these image recognition tasks while generating an attention map for visual explanation. Our code is availablehttps://github.com/machine-perception-robotics-group/attention_branch_network.

READ FULL TEXT

page 1

page 2

page 3

page 4

page 5

page 6

page 8

page 9

research
05/09/2019

Embedding Human Knowledge in Deep Neural Network via Attention Map

Human-in-the-loop (HITL), which introduces human knowledge to machine le...
research
05/03/2021

LFI-CAM: Learning Feature Importance for Better Visual Explanation

Class Activation Mapping (CAM) is a powerful technique used to understan...
research
10/20/2022

Towards Better Guided Attention and Human Knowledge Insertion in Deep Convolutional Neural Networks

Attention Branch Networks (ABNs) have been shown to simultaneously provi...
research
08/07/2021

Information Bottleneck Approach to Spatial Attention Learning

The selective visual attention mechanism in the human visual system (HVS...
research
04/09/2018

AMNet: Memorability Estimation with Attention

In this paper we present the design and evaluation of an end-to-end trai...
research
05/22/2019

AttentionRNN: A Structured Spatial Attention Mechanism

Visual attention mechanisms have proven to be integrally important const...
research
03/30/2017

Dynamic Computational Time for Visual Attention

We propose a dynamic computational time model to accelerate the average ...

Please sign up or login with your details

Forgot password? Click here to reset