文献类型：期刊文献

英文题名：BMPCN: A Bigraph Mutual Prototype Calibration Net for few-shot classification

作者：Zhang, Jing[1];Chen, Mingzhe[1];Hu, Yunzuo[1];Zhang, Xinzhou[1];Wang, Zhe[1]

机构：[1]East China Univ Sci & Technol, Shanghai 200237, Peoples R China

年份：2024

卷号：156

外文期刊名：PATTERN RECOGNITION

收录：;EI(收录号：20243216812264);WOS:【SCI-EXPANDED(收录号:WOS:001288010500001)】；

基金：This research is supported by Natural Science Foundation of Shanghai, China "Research on image sentiment analysis and expression based on human vision and cognitive psychology" under Grant No. 22ZR1418400.

语种：英文

外文关键词：Few-shot learning; Bigraph Mutual Prototype Calibration Net; Bigraph Mutual Promotion; Proto-level similarity

摘要：In recent studies on few-shot classification, most of the existing methods utilized word embeddings as prior knowledge to adjust the distribution of visual prototypes. However, this straightforward fusion of visual and semantic features profoundly alters the feature distribution in the original feature space, rendering it unable to effectively calibrate feature distribution through mutual guidance of cross-modal information. To address this problem, we propose a novel Bigraph Mutual Prototype Calibration Network (BMPCN) for few-shot learning in this paper, in which we not only update the distribution of class features based on prototype-level similarity in both visual and semantic spaces but also facilitate the mutual guidance of visual and semantic feature updates through instance-level similarity. In the BMPCN, a bigraph mutual promotion structure is proposed, wherein a visual graph is constructed with visual features as nodes and the similarity between visual features as edges. Simultaneously, the semantic feature nodes are automatically generated from images, and the class- level prior knowledge is leveraged to correct these automatically generated semantic nodes. To better update the bigraph mutual promotion structure, we propose a Bigraph Interactive Augmentation Module (BIAM), a Nearest Neighbor Proto-level Similarity Promotion Module (NN-PSP), and a Proto-level Similarity Promotion Module (PK-PSP) based on original knowledge augmentation to perform the bigraph update. For inter-graph updating, we use the prototype-level similarity obtained from the NN-PSP and PK-PSP modules to fully learn task-level information, thus enabling task-specific prototype updates. For intra-graph updating, our visual and semantic graphs use instance-level similarity analysis to extract potential correlations between different feature domains and implement mutual guidance in the BIAM module to correct the feature distribution of visual and semantic features. Experiments on three widely used benchmarks illustrated that our proposed method obtains excellent performance based on the backbone Conv-4, and the results outperform state-of-theart methods by about 8% on miniImageNet, tieredImageNet, and CUB-200-2011. Code has been available at https://github.com/cmzHome/BMPCN-MASTER.