Technology Category
Machine Learning: Transfer, Domain Adaptation, Multi-Task LearningComputer Vision: Multi-modal VisionApplication Domains: Security
FAD: Frequency Adaptation and Diversion for Cross-domain Few-shot Learning
🤖 AI Summary
Cross-domain few-shot learning (CD-FSL) confronts dual challenges: severe distribution shift between source and target domains and extreme scarcity of labeled examples. Existing spatial-domain adaptation methods neglect spectral characteristic discrepancies, limiting generalization. To address this, we propose the first frequency-domain disentangled adaptation framework: features are decomposed into low-, mid-, and high-frequency subbands via DFT/IDFT; radial frequency-band masking and multi-scale convolutional branches enable decoupled, parallel, and lightweight adaptive modulation per band; crucially, it supports spectrum-scale-aware, kernel-level customization—novel in CD-FSL. Evaluated on Meta-Dataset, our method consistently outperforms state-of-the-art approaches across both seen and unseen domains, achieving significant accuracy gains. This demonstrates that explicit frequency-domain modeling delivers critical improvements to CD-FSL generalization.
Technology Category
Application Category
📝 Abstract
Cross-domain few-shot learning (CD-FSL) requires models to generalize from limited labeled samples under significant distribution shifts. While recent methods enhance adaptability through lightweight task-specific modules, they operate solely in the spatial domain and overlook frequency-specific variations that are often critical for robust transfer. We observe that spatially similar images across domains can differ substantially in their spectral representations, with low and high frequencies capturing complementary semantic information at coarse and fine levels. This indicates that uniform spatial adaptation may overlook these spectral distinctions, thus constraining generalization. To address this, we introduce Frequency Adaptation and Diversion (FAD), a frequency-aware framework that explicitly models and modulates spectral components. At its core is the Frequency Diversion Adapter, which transforms intermediate features into the frequency domain using the discrete Fourier transform (DFT), partitions them into low, mid, and high-frequency bands via radial masks, and reconstructs each band using inverse DFT (IDFT). Each frequency band is then adapted using a dedicated convolutional branch with a kernel size tailored to its spectral scale, enabling targeted and disentangled adaptation across frequencies. Extensive experiments on the Meta-Dataset benchmark demonstrate that FAD consistently outperforms state-of-the-art methods on both seen and unseen domains, validating the utility of frequency-domain representations and band-wise adaptation for improving generalization in CD-FSL.
Problem
Research questions and friction points this paper is trying to address.
Addresses cross-domain few-shot learning under distribution shifts
Overlooked frequency-specific variations in spatial domain methods
Proposes frequency-aware adaptation for robust spectral transfer
Innovation
Methods, ideas, or system contributions that make the work stand out.
Frequency Diversion Adapter modulates spectral components
Discrete Fourier Transform partitions frequency bands
Band-wise convolutional adaptation enhances generalization
🔎 Similar Papers
No similar papers found.
