1 code implementation • 30 Nov 2023 • Hai Zhang, Junzhe Xu, Shanlin Jiang, Zhenan He
This limitation severely constrains the potential of semantics in Few-Shot Learning.
no code implementations • 11 Oct 2023 • Junzhe Xu, Suling Duan, Chenwei Tang, Zhenan He, Jiancheng Lv
Second, we propose Attribute Revision Module (ARM), which generates image-level semantics by revising the ground-truth value of each attribute, compensating for performance degradation caused by ignoring intra-class variation.