FreeKD: Knowledge Distillation via Semantic Frequency Prompt

• URL: http://arxiv.org/abs/2311.12079v2
• Date: Wed, 22 May 2024 13:43:01 GMT
• Title: FreeKD: Knowledge Distillation via Semantic Frequency Prompt
• Abstract summary: We propose a Frequency Knowledge Distillation method as FreeKD, which determines the optimal localization and extent for the frequency distillation. We also employ a position-aware relational frequency loss for dense prediction tasks, delivering a high-order spatial enhancement to the student model.
• Score: 33.28298466424745
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Knowledge distillation (KD) has been applied to various tasks successfully, and mainstream methods typically boost the student model via spatial imitation losses. However, the consecutive downsamplings induced in the spatial domain of teacher model is a type of corruption, hindering the student from analyzing what specific information needs to be imitated, which results in accuracy degradation. To better understand the underlying pattern of corrupted feature maps, we shift our attention to the frequency domain. During frequency distillation, we encounter a new challenge: the low-frequency bands convey general but minimal context, while the high are more informative but also introduce noise. Not each pixel within the frequency bands contributes equally to the performance. To address the above problem: (1) We propose the Frequency Prompt plugged into the teacher model, absorbing the semantic frequency context during finetuning. (2) During the distillation period, a pixel-wise frequency mask is generated via Frequency Prompt, to localize those pixel of interests (PoIs) in various frequency bands. Additionally, we employ a position-aware relational frequency loss for dense prediction tasks, delivering a high-order spatial enhancement to the student model. We dub our Frequency Knowledge Distillation method as FreeKD, which determines the optimal localization and extent for the frequency distillation. Extensive experiments demonstrate that FreeKD not only outperforms spatial-based distillation methods consistently on dense prediction tasks (e.g., FreeKD brings 3.8 AP gains for RepPoints-R50 on COCO2017 and 4.55 mIoU gains for PSPNet-R18 on Cityscapes), but also conveys more robustness to the student. Notably, we also validate the generalization of our approach on large-scale vision models (e.g., DINO and SAM).

Related papers

• Class-frequency Guided Noise Schedule for Diffusion Models [83.19018650759415]
  We first examine the correlations between class frequency and the multi-scale noise schedule within diffusion models.<n>We propose the textitClass-frequency Guided (CFRG) noise schedule, leveraging the insight that low-frequency classes should be endowed with larger-scale noises.
  arXiv  Detail & Related papers  (2026-06-26T03:43:23Z)
• Freqformer: Image-Demoiréing Transformer via Efficient Frequency Decomposition [83.40450475728792]
  We present Freqformer, a Transformer-based framework specifically designed for image demoir'eing through targeted frequency separation.<n>Our method performs an effective frequency decomposition that explicitly splits moir'e patterns into high-frequency spatially-localized textures and low-frequency scale-robust color distortions.<n>Experiments on various demoir'eing benchmarks demonstrate that Freqformer achieves state-of-the-art performance with a compact model size.
  arXiv  Detail & Related papers  (2025-05-25T12:23:10Z)
• FiGKD: Fine-Grained Knowledge Distillation via High-Frequency Detail Transfer [0.0]
  Fine-Grained Knowledge Distillation (FiGKD) is a frequency-aware framework that decomposes a model's logits into low-frequency (content) and high-frequency (detail) components.<n>FiGKD consistently outperforms state-of-the-art logit-based and feature-based distillation methods across a variety of teacher-student configurations.
  arXiv  Detail & Related papers  (2025-05-17T08:27:02Z)
• Sharpening Neural Implicit Functions with Frequency Consolidation Priors [53.6277160912059]
  Signed Distance Functions (SDFs) are vital implicit representations to represent high fidelity 3D surfaces. Current methods mainly leverage a neural network to learn an SDF from various supervisions including signed, 3D point clouds, or multi-view images. We introduce a method to sharpen a low frequency SDF observation by recovering its high frequency components, pursuing a sharper and more complete surface.
  arXiv  Detail & Related papers  (2024-12-27T16:18:46Z)
• Towards Combating Frequency Simplicity-biased Learning for Domain Generalization [36.777767173275336]
  Domain generalization methods aim to learn transferable knowledge from source domains that can generalize well to unseen target domains. Recent studies show that neural networks frequently suffer from a simplicity-biased learning behavior which leads to over-reliance on specific frequency sets. We propose two effective data augmentation modules designed to collaboratively and adaptively adjust the frequency characteristic of the dataset.
  arXiv  Detail & Related papers  (2024-10-21T16:17:01Z)
• Tuning Frequency Bias of State Space Models [48.60241978021799]
  State space models (SSMs) leverage linear, time-invariant (LTI) systems to learn sequences with long-range dependencies. We find that SSMs exhibit an implicit bias toward capturing low-frequency components more effectively than high-frequency ones.
  arXiv  Detail & Related papers  (2024-10-02T21:04:22Z)
• 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)
• What do neural networks learn in image classification? A frequency shortcut perspective [3.9858496473361402]
  This study empirically investigates the learning dynamics of frequency shortcuts in neural networks (NNs) We show that NNs tend to find simple solutions for classification, and what they learn first during training depends on the most distinctive frequency characteristics. We propose a metric to measure class-wise frequency characteristics and a method to identify frequency shortcuts.
  arXiv  Detail & Related papers  (2023-07-19T08:34:25Z)
• 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)
• Exploring Inconsistent Knowledge Distillation for Object Detection with Data Augmentation [66.25738680429463]
  Knowledge Distillation (KD) for object detection aims to train a compact detector by transferring knowledge from a teacher model. We propose inconsistent knowledge distillation (IKD) which aims to distill knowledge inherent in the teacher model's counter-intuitive perceptions. Our method outperforms state-of-the-art KD baselines on one-stage, two-stage and anchor-free object detectors.
  arXiv  Detail & Related papers  (2022-09-20T16:36:28Z)
• 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)
• Wavelet Knowledge Distillation: Towards Efficient Image-to-Image Translation [22.841122397104265]
  This paper investigates GANs performance from a frequency perspective. The results show that GANs, especially small GANs lack the ability to generate high-quality high frequency information. We propose a novel knowledge distillation method referred to as wavelet knowledge distillation.
  arXiv  Detail & Related papers  (2022-03-12T02:42:04Z)
• Robust Learning with Frequency Domain Regularization [1.370633147306388]
  We introduce a new regularization method by constraining the frequency spectra of the filter of the model. We demonstrate the effectiveness of our regularization by (1) defensing to adversarial perturbations; (2) reducing the generalization gap in different architecture; and (3) improving the generalization ability in transfer learning scenario without fine-tune.
  arXiv  Detail & Related papers  (2020-07-07T07:29:20Z)

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.