Fourier-Attentive Representation Learning: A Fourier-Guided Framework for Few-Shot Generalization in Vision-Language Models
This work addresses the challenge of improving few-shot learning in vision-language models for researchers and practitioners by providing a novel disentanglement method, though it appears incremental as it builds on existing VLM frameworks.
The paper tackles the problem of entangled domain-invariant and domain-specific features in vision-language models by proposing Fourier-Attentive Representation Learning (FARL), which uses Fourier analysis and a dual cross-attention mechanism to disentangle visual representations, resulting in enhanced few-shot generalization as demonstrated on 15 datasets.
Large-scale pre-trained Vision-Language Models (VLMs) have demonstrated strong few-shot learning capabilities. However, these methods typically learn holistic representations where an image's domain-invariant structure is implicitly entangled with its domain-specific style. This presents an opportunity to further enhance generalization by disentangling these visual cues. In this paper, we propose Fourier-Attentive Representation Learning (FARL), a novel framework that addresses this by explicitly disentangling visual representations using Fourier analysis. The core of our method is a dual cross-attention mechanism, where learnable representation tokens separately query an image's structural features (from the phase spectrum) and stylistic features (from the amplitude spectrum). This process yields enriched, disentangled tokens that are then injected deep into the VLM encoders to guide adaptation. Our design, which includes an asymmetric injection strategy, forces the model to learn a more robust vision-language alignment. Extensive experiments on 15 datasets demonstrate the effectiveness of our approach.