Like Humans to Few-Shot Learning through Knowledge Permeation of Vision and Text
This work addresses the challenge of generalizing recognizers to novel categories with limited data, which is incremental in improving few-shot learning methods.
The paper tackles the problem of few-shot learning by proposing a bidirectional knowledge permeation strategy (BiKop) to better integrate visual and textual knowledge, achieving remarkable superiority on four challenging benchmarks.
Few-shot learning aims to generalize the recognizer from seen categories to an entirely novel scenario. With only a few support samples, several advanced methods initially introduce class names as prior knowledge for identifying novel classes. However, obstacles still impede achieving a comprehensive understanding of how to harness the mutual advantages of visual and textual knowledge. In this paper, we propose a coherent Bidirectional Knowledge Permeation strategy called BiKop, which is grounded in a human intuition: A class name description offers a general representation, whereas an image captures the specificity of individuals. BiKop primarily establishes a hierarchical joint general-specific representation through bidirectional knowledge permeation. On the other hand, considering the bias of joint representation towards the base set, we disentangle base-class-relevant semantics during training, thereby alleviating the suppression of potential novel-class-relevant information. Experiments on four challenging benchmarks demonstrate the remarkable superiority of BiKop. Our code will be publicly available.