江汉大学学报（自然科学版）2023，Vol.51Issue(6)：63-71,9.DOI:10.16389/j.cnki.cn42-1737/n.2023.06.009
基于互通道损失数据增强网络的细粒度图像分类
Fine-grained Image Classification Based on Mutual Channel Loss Data Augmentation Network
摘要
Abstract
Finding discriminative local regions corresponding to fine-grained features is the key to solve fine-grained image classification problems.Recently,fine-grained classification by weakly supervised data augmentation network(WS-DAN)has achieved excellent results,but its single cross-entropy loss(CE-Loss)makes the network focus on global discriminative regions and misses some local discriminative regions.To address this problem,this paper proposed a data augmentation network(MC-DAN)based on mutual channel loss(MC-Loss),which could force feature channels belonging to the same class to be more discriminative.Second,a counterfactual attention mechanism(CAL)was introduced to encourage the network to learn more attention information by counterfactual intervention.In addition,an attention module combining spatial attention and channel attention was proposed to better focus on object regions in images.Comprehensive experiments on three public datasets showed that the method could effectively achieve classification.关键词
细粒度图像分类/互通道损失/反事实注意力学习/数据增强Key words
fine-grained image classification/mutual channel loss/counterfactual attention learning/data augmentation分类
信息技术与安全科学引用本文复制引用
胡晓斌,彭太乐..基于互通道损失数据增强网络的细粒度图像分类[J].江汉大学学报（自然科学版）,2023,51(6):63-71,9.基金项目
国家自然科学基金资助项目(61976101) （61976101）
安徽省高校自然科学研究项目(KJ2017A843) （KJ2017A843）
