Efficient Continual Learning through Frequency Decomposition and Integration

• URL: http://arxiv.org/abs/2503.22175v1
• Date: Fri, 28 Mar 2025 06:36:33 GMT
• Title: Efficient Continual Learning through Frequency Decomposition and Integration
• Authors: Ruiqi Liu, Boyu Diao, Libo Huang, Hangda Liu, Chuanguang Yang, Zhulin An, Yongjun Xu,
• Abstract summary: We propose the Frequency Decomposition and Integration Network (FDINet), a novel framework that decomposes and integrates information across frequencies.<n> 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%.
• Score: 25.016256446470948
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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$\times$.

Related papers

• Spatiotemporal Attention Learning Framework for Event-Driven Object Recognition [1.0445957451908694]
  Event-based vision sensors capture local pixel-level intensity changes as a sparse event stream containing position, polarity, and information. This paper presents a novel learning framework for event-based object recognition, utilizing a VARGG network enhanced with Contemporalal Block Attention Module (CBAM) Our approach achieves comparable performance to state-of-the-art ResNet-based methods while reducing parameter count by 2.3% compared to the original VGG model.
  arXiv  Detail & Related papers  (2025-04-01T02:37:54Z)
• STAF: Sinusoidal Trainable Activation Functions for Implicit Neural Representation [7.2888019138115245]
  Implicit Neural Representations (INRs) have emerged as a powerful framework for modeling continuous signals. The spectral bias of ReLU-based networks is a well-established limitation, restricting their ability to capture fine-grained details in target signals. We introduce Sinusoidal Trainable Functions Activation (STAF) STAF inherently modulates its frequency components, allowing for self-adaptive spectral learning.
  arXiv  Detail & Related papers  (2025-02-02T18:29:33Z)
• BEAT: Balanced Frequency Adaptive Tuning for Long-Term Time-Series Forecasting [46.922741972636025]
  Time-series forecasting is crucial for numerous real-world applications including weather prediction and financial market modeling. We propose BEAT (Balanced frEquency Adaptive Tuning), a novel framework that monitors the training status for each frequency and adaptively adjusts their gradient updates. BEAT consistently outperforms state-of-the-art approaches in experiments on seven real-world datasets.
  arXiv  Detail & Related papers  (2025-01-31T11:52:35Z)
• Continual Learning in the Frequency Domain [22.415936450558334]
  We propose a novel framework called Continual Learning in the Frequency Domain (CLFD) For the input features of the feature extractor, CLFD employs wavelet transform to map the original input image into the frequency domain. Experiments conducted in both cloud and edge environments demonstrate that CLFD consistently improves the performance of state-of-the-art (SOTA) methods in both precision and training efficiency.
  arXiv  Detail & Related papers  (2024-10-09T07:57:47Z)
• Frequency-Aware Deepfake Detection: Improving Generalizability through Frequency Space Learning [81.98675881423131]
  This research addresses the challenge of developing a universal deepfake detector that can effectively identify unseen deepfake images. Existing frequency-based paradigms have relied on frequency-level artifacts introduced during the up-sampling in GAN pipelines to detect forgeries. We introduce a novel frequency-aware approach called FreqNet, centered around frequency domain learning, specifically designed to enhance the generalizability of deepfake detectors.
  arXiv  Detail & Related papers  (2024-03-12T01:28:00Z)
• A High-Frequency Focused Network for Lightweight Single Image Super-Resolution [16.264904771818507]
  High-frequency detail is much more difficult to reconstruct than low-frequency information. Most SISR models allocate equal computational resources for low-frequency and high-frequency information. We propose a novel High-Frequency Focused Network (HFFN) that selectively enhance high-frequency information.
  arXiv  Detail & Related papers  (2023-03-21T09:41:13Z)
• Disentangled Representation Learning for RF Fingerprint Extraction under Unknown Channel Statistics [77.13542705329328]
  We propose a framework of disentangled representation learning(DRL) that first learns to factor the input signals into a device-relevant component and a device-irrelevant component via adversarial learning. The implicit data augmentation in the proposed framework imposes a regularization on the RFF extractor to avoid the possible overfitting of device-irrelevant channel statistics. Experiments validate that the proposed approach, referred to as DR-RFF, outperforms conventional methods in terms of generalizability to unknown complicated propagation environments.
  arXiv  Detail & Related papers  (2022-08-04T15:46:48Z)
• Improved Speech Emotion Recognition using Transfer Learning and Spectrogram Augmentation [56.264157127549446]
  Speech emotion recognition (SER) is a challenging task that plays a crucial role in natural human-computer interaction. One of the main challenges in SER is data scarcity. We propose a transfer learning strategy combined with spectrogram augmentation.
  arXiv  Detail & Related papers  (2021-08-05T10:39:39Z)
• Collaborative Distillation in the Parameter and Spectrum Domains for Video Action Recognition [79.60708268515293]
  This paper explores how to train small and efficient networks for action recognition. We propose two distillation strategies in the frequency domain, namely the feature spectrum and parameter distribution distillations respectively. Our method can achieve higher performance than state-of-the-art methods with the same backbone.
  arXiv  Detail & Related papers  (2020-09-15T07:29:57Z)
• Capturing scattered discriminative information using a deep architecture in acoustic scene classification [49.86640645460706]
  In this study, we investigate various methods to capture discriminative information and simultaneously mitigate the overfitting problem. We adopt a max feature map method to replace conventional non-linear activations in a deep neural network. Two data augment methods and two deep architecture modules are further explored to reduce overfitting and sustain the system's discriminative power.
  arXiv  Detail & Related papers  (2020-07-09T08:32:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.