Mengya Han, Yibing Zhan, Baosheng Yu, Yong Luo, Han Hu, Bo Du, Yonggang Wen, Dacheng Tao. Region-adaptive Concept Aggregation for Few-shot Visual Recognition[J]. Machine Intelligence Research, 2023, 20(4): 554-568. DOI: 10.1007/s11633-022-1358-8
Citation: Mengya Han, Yibing Zhan, Baosheng Yu, Yong Luo, Han Hu, Bo Du, Yonggang Wen, Dacheng Tao. Region-adaptive Concept Aggregation for Few-shot Visual Recognition[J]. Machine Intelligence Research, 2023, 20(4): 554-568. DOI: 10.1007/s11633-022-1358-8

Region-adaptive Concept Aggregation for Few-shot Visual Recognition

  • Few-shot learning (FSL) aims to learn novel concepts from very limited examples. However, most FSL methods suffer from the issue of lacking robustness in concept learning. Specifically, existing FSL methods usually ignore the diversity of region contents that may contain concept-irrelevant information such as the background, which would introduce bias/noise and degrade the performance of conceptual representation learning. To address the above-mentioned issue, we propose a novel metric-based FSL method termed region-adaptive concept aggregation network or RCA-Net. Specifically, we devise a region-adaptive concept aggregator (RCA) to model the relationships of different regions and capture the conceptual information in different regions, which are then integrated in a weighted average manner to obtain the conceptual representation. Consequently, robust concept learning can be achieved by focusing more on the concept-relevant information and less on the conceptual-irrelevant information. We perform extensive experiments on three popular visual recognition benchmarks to demonstrate the superiority of RCA-Net for robust few-shot learning. In particular, on the Caltech-UCSD Birds-200-2011 (CUB200) dataset, the proposed RCA-Net significantly improves 1-shot accuracy from 74.76% to 78.03% and 5-shot accuracy from 86.84% to 89.83% compared with the most competitive counterpart.
  • loading

Catalog

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return