Information Symmetry Matters: A Modal-Alternating Propagation Network for Few-Shot Learning

Zhong Ji, Zhishen Hou, Xiyao Liu*, Yanwei Pang, Jungong Han

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

21 Citations (SciVal)
17 Downloads (Pure)

Abstract

Semantic information provides intra-class consistency and inter-class discriminability beyond visual concepts, which has been employed in Few-Shot Learning (FSL) to achieve further gains. However, semantic information is only available for labeled samples but absent for unlabeled samples, in which the embeddings are rectified unilaterally by guiding the few labeled samples with semantics. Therefore, it is inevitable to bring a cross-modal bias between semantic-guided samples and nonsemantic-guided samples, which results in an information asymmetry problem. To address this problem, we propose a Modal-Alternating Propagation Network (MAP-Net) to supplement the absent semantic information of unlabeled samples, which builds information symmetry among all samples in both visual and semantic modalities. Specifically, the MAP-Net transfers the neighbor information by the graph propagation to generate the pseudo-semantics for unlabeled samples guided by the completed visual relationships and rectify the feature embeddings. In addition, due to the large discrepancy between visual and semantic modalities, we design a Relation Guidance (RG) strategy to guide the visual relation vectors via semantics so that the propagated information is more beneficial. Extensive experimental results on three semantic-labeled datasets, i.e., Caltech-UCSD-Birds 200-2011, SUN Attribute Database and Oxford 102 Flower, have demonstrated that our proposed method achieves promising performance and outperforms the state-of-the-art approaches, which indicates the necessity of information symmetry.

Original languageEnglish
Pages (from-to)1520-1531
Number of pages12
JournalIEEE Transactions on Image Processing
Volume31
Early online date20 Jan 2022
DOIs
Publication statusPublished - 2022

Keywords

  • Correlation
  • Learning systems
  • Semantics
  • Sun
  • Task analysis
  • Training
  • Visualization

Fingerprint

Dive into the research topics of 'Information Symmetry Matters: A Modal-Alternating Propagation Network for Few-Shot Learning'. Together they form a unique fingerprint.

Cite this