Color as the Impetus: Transforming Few-Shot Learner

TL;DR

This paper introduces the ColorSense Learner, a bio-inspired meta-learning framework leveraging color perception to improve few-shot learning, demonstrating strong generalization and robustness across multiple benchmarks.

Contribution

It pioneers a novel color-based meta-learning approach and proposes the ColorSense Distiller for enhanced intra-class and inter-class feature discrimination.

Findings

Strong generalization across eleven benchmarks

Robustness and transferability in few-shot classification

Effective filtering of irrelevant features through color channels

Abstract

Humans possess innate meta-learning capabilities, partly attributable to their exceptional color perception. In this paper, we pioneer an innovative viewpoint on few-shot learning by simulating human color perception mechanisms. We propose the ColorSense Learner, a bio-inspired meta-learning framework that capitalizes on inter-channel feature extraction and interactive learning. By strategically emphasizing distinct color information across different channels, our approach effectively filters irrelevant features while capturing discriminative characteristics. Color information represents the most intuitive visual feature, yet conventional meta-learning methods have predominantly neglected this aspect, focusing instead on abstract feature differentiation across categories. Our framework bridges the gap via synergistic color-channel interactions, enabling better intra-class commonality extraction and larger inter-class differences. Furthermore, we introduce a meta-distiller based on knowledge distillation, ColorSense Distiller, which incorporates prior teacher knowledge to augment the student network's meta-learning capacity. We've conducted comprehensive coarse/fine-grained and cross-domain experiments on eleven few-shot benchmarks for validation. Numerous experiments reveal that our methods have extremely strong generalization ability, robustness, and transferability, and effortless handle few-shot classification from the perspective of color perception.