Continual Learning in the Frequency Domain

• URL: http://arxiv.org/abs/2410.06645v3
• Date: Wed, 30 Oct 2024 08:32:36 GMT
• Title: Continual Learning in the Frequency Domain
• Authors: Ruiqi Liu, Boyu Diao, Libo Huang, Zijia An, Zhulin An, Yongjun Xu,
• Abstract summary: 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.
• Score: 22.415936450558334
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Continual learning (CL) is designed to learn new tasks while preserving existing knowledge. Replaying samples from earlier tasks has proven to be an effective method to mitigate the forgetting of previously acquired knowledge. However, the current research on the training efficiency of rehearsal-based methods is insufficient, which limits the practical application of CL systems in resource-limited scenarios. The human visual system (HVS) exhibits varying sensitivities to different frequency components, enabling the efficient elimination of visually redundant information. Inspired by HVS, we propose a novel framework called Continual Learning in the Frequency Domain (CLFD). To our knowledge, this is the first study to utilize frequency domain features to enhance the performance and efficiency of CL training on edge devices. For the input features of the feature extractor, CLFD employs wavelet transform to map the original input image into the frequency domain, thereby effectively reducing the size of input feature maps. Regarding the output features of the feature extractor, CLFD selectively utilizes output features for distinct classes for classification, thereby balancing the reusability and interference of output features based on the frequency domain similarity of the classes across various tasks. Optimizing only the input and output features of the feature extractor allows for seamless integration of CLFD with various rehearsal-based methods. Extensive 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. Specifically, CLFD can increase the accuracy of the SOTA CL method by up to 6.83% and reduce the training time by 2.6$\times$.

Related papers

• Frequency-Guided Masking for Enhanced Vision Self-Supervised Learning [49.275450836604726]
  We present a novel frequency-based Self-Supervised Learning (SSL) approach that significantly enhances its efficacy for pre-training. We employ a two-branch framework empowered by knowledge distillation, enabling the model to take both the filtered and original images as input.
  arXiv  Detail & Related papers  (2024-09-16T15:10:07Z)
• Exploring Cross-Domain Few-Shot Classification via Frequency-Aware Prompting [37.721042095518044]
  Cross-Domain Few-Shot Learning has witnessed great stride with the development of meta-learning. We propose a Frequency-Aware Prompting method with mutual attention for Cross-Domain Few-Shot classification.
  arXiv  Detail & Related papers  (2024-06-24T08:14:09Z)
• Enhancing Out-of-Distribution Detection with Multitesting-based Layer-wise Feature Fusion [11.689517005768046]
  Out-of-distribution samples may exhibit shifts in local or global features compared to the training distribution. We propose a novel framework, Multitesting-based Layer-wise Out-of-Distribution (OOD) Detection. Our scheme effectively enhances the performance of out-of-distribution detection when compared to baseline methods.
  arXiv  Detail & Related papers  (2024-03-16T04:35:04Z)
• Knowledge Diffusion for Distillation [53.908314960324915]
  The representation gap between teacher and student is an emerging topic in knowledge distillation (KD) We state that the essence of these methods is to discard the noisy information and distill the valuable information in the feature. We propose a novel KD method dubbed DiffKD, to explicitly denoise and match features using diffusion models.
  arXiv  Detail & Related papers  (2023-05-25T04:49:34Z)
• Transfer Learning for Autonomous Chatter Detection in Machining [0.9281671380673306]
  Large-amplitude chatter vibrations are one of the most important phenomena in machining processes. Three challenges can be identified in applying machine learning for chatter detection at large in industry. These three challenges can be grouped under the umbrella of transfer learning.
  arXiv  Detail & Related papers  (2022-04-11T20:46:06Z)
• Adaptive Frequency Learning in Two-branch Face Forgery Detection [66.91715092251258]
  We propose Adaptively learn Frequency information in the two-branch Detection framework, dubbed AFD. We liberate our network from the fixed frequency transforms, and achieve better performance with our data- and task-dependent transform layers.
  arXiv  Detail & Related papers  (2022-03-27T14:25:52Z)
• Deep Frequency Filtering for Domain Generalization [55.66498461438285]
  Deep Neural Networks (DNNs) have preferences for some frequency components in the learning process. We propose Deep Frequency Filtering (DFF) for learning domain-generalizable features. We show that applying our proposed DFF on a plain baseline outperforms the state-of-the-art methods on different domain generalization tasks.
  arXiv  Detail & Related papers  (2022-03-23T05:19:06Z)
• Functional Regularization for Reinforcement Learning via Learned Fourier Features [98.90474131452588]
  We propose a simple architecture for deep reinforcement learning by embedding inputs into a learned Fourier basis. We show that it improves the sample efficiency of both state-based and image-based RL.
  arXiv  Detail & Related papers  (2021-12-06T18:59:52Z)
• On Transfer Learning of Traditional Frequency and Time Domain Features in Turning [1.0965065178451106]
  We use traditional signal processing tools to identify chatter in accelerometer signals obtained from a turning experiment. The tagged signals are then used to train a classifier. Our results show that features extracted from the Fourier spectrum are the most informative when training a classifier and testing on data from the same cutting configuration.
  arXiv  Detail & Related papers  (2020-08-28T14:47:57Z)
• iffDetector: Inference-aware Feature Filtering for Object Detection [70.8678270164057]
  We introduce a generic Inference-aware Feature Filtering (IFF) module that can easily be combined with modern detectors. IFF performs closed-loop optimization by leveraging high-level semantics to enhance the convolutional features. IFF can be fused with CNN-based object detectors in a plug-and-play manner with negligible computational cost overhead.
  arXiv  Detail & Related papers  (2020-06-23T02:57:29Z)

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.