2025/03/28 by Ruiqi Liu, Liu, Ruiqi, Boyu Diao +11 · 1 citation
Computer Science · #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Face recognition and analysis
paper · pdf · doi:10.48550/arxiv.2503.22175
openalex publication_date 2025/03/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Continual learning (CL) aims to learn new tasks while retaining past knowledge, addressing the challenge of forgetting during task adaptation. Rehearsal-based methods, which replay previous samples, effectively mitigate forgetting. However, research on enhancing the efficiency of these methods, especially in resource-constrained environments, remains limited, hindering their application in real-world systems with dynamic data streams. The human perceptual system processes visual scenes through complementary frequency channels: low-frequency signals capture holistic cues, while high-frequency components convey structural details vital for fine-grained discrimination. Inspired by this, we propose the Frequency Decomposition and Integration Network (FDINet), a novel framework that decomposes and integrates information across frequencies. FDINet designs two lightweight networks to independently process low- and high-frequency components of images. When integrated with rehearsal-based methods, this frequency-aware design effectively enhances cross-task generalization through low-frequency information, preserves class-specific details using high-frequency information, and facilitates efficient training due to its lightweight architecture. Experiments demonstrate that FDINet reduces backbone parameters by 78%, improves accuracy by up to 7.49% over state-of-the-art (SOTA) methods, and decreases peak memory usage by up to 80%. Additionally, on edge devices, FDINet accelerates training by up to 5×.