Kaiyang Liao , Yunfei Tan , Yuanlin Zheng , Dingwen Song
{"title":"Cross-sample feature interaction enhancement for few-shot fine-grained classification","authors":"Kaiyang Liao , Yunfei Tan , Yuanlin Zheng , Dingwen Song","doi":"10.1016/j.displa.2025.103157","DOIUrl":null,"url":null,"abstract":"<div><div>Few-shot fine-grained image classification faces challenges due to high inter-class feature similarity, significant intra-class variations, and limited data, leading to insufficient model generalization. To address the challenges of category aggregation and separation in few-shot fine-grained scenarios, this paper proposes a classification network enhanced by cross-sample feature interaction. The cross-sample feature interaction enhancement process includes three core components: the Cross-domain Feature Attention Network (CFAN), which enhances feature consistency between support and query sets through channel and spatial attention mechanisms, focusing on capturing critical detail regions; the Global Dependency Augmentation Module (GDAM), which explicitly models dependencies between distant pixels and integrates local and global information; and the Cross-class Interaction Module (CCIM), which uses a bidirectional self-attention mechanism to align local features of query and support samples through complementary and interactive cross-sample features. Additionally, dynamic generation of inter-class feature contrast relationships improves inter-class feature discrimination. Experimental results demonstrate that the proposed method achieves superior performance compared to mainstream methods on multiple public few-shot fine-grained classification datasets, with particularly remarkable results under extremely few-shot conditions. The proposed method significantly improves the accuracy and robustness of few-shot fine-grained classification through an efficient feature interaction mechanism.</div></div>","PeriodicalId":50570,"journal":{"name":"Displays","volume":"90 ","pages":"Article 103157"},"PeriodicalIF":3.7000,"publicationDate":"2025-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Displays","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0141938225001945","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, HARDWARE & ARCHITECTURE","Score":null,"Total":0}
引用次数: 0
Abstract
Few-shot fine-grained image classification faces challenges due to high inter-class feature similarity, significant intra-class variations, and limited data, leading to insufficient model generalization. To address the challenges of category aggregation and separation in few-shot fine-grained scenarios, this paper proposes a classification network enhanced by cross-sample feature interaction. The cross-sample feature interaction enhancement process includes three core components: the Cross-domain Feature Attention Network (CFAN), which enhances feature consistency between support and query sets through channel and spatial attention mechanisms, focusing on capturing critical detail regions; the Global Dependency Augmentation Module (GDAM), which explicitly models dependencies between distant pixels and integrates local and global information; and the Cross-class Interaction Module (CCIM), which uses a bidirectional self-attention mechanism to align local features of query and support samples through complementary and interactive cross-sample features. Additionally, dynamic generation of inter-class feature contrast relationships improves inter-class feature discrimination. Experimental results demonstrate that the proposed method achieves superior performance compared to mainstream methods on multiple public few-shot fine-grained classification datasets, with particularly remarkable results under extremely few-shot conditions. The proposed method significantly improves the accuracy and robustness of few-shot fine-grained classification through an efficient feature interaction mechanism.
期刊介绍:
Displays is the international journal covering the research and development of display technology, its effective presentation and perception of information, and applications and systems including display-human interface.
Technical papers on practical developments in Displays technology provide an effective channel to promote greater understanding and cross-fertilization across the diverse disciplines of the Displays community. Original research papers solving ergonomics issues at the display-human interface advance effective presentation of information. Tutorial papers covering fundamentals intended for display technologies and human factor engineers new to the field will also occasionally featured.