Channel-wise Dynamic Knowledge Distillation via Adaptive Sample Generation for Action Recognition

• URL: http://arxiv.org/abs/2608.03100v1
• Date: Tue, 04 Aug 2026 04:18:13 GMT
• Title: Channel-wise Dynamic Knowledge Distillation via Adaptive Sample Generation for Action Recognition
• Abstract summary: We develop an Adaptive Sample-aware Channel-wise Dynamic (ASCD) KD approach, which operates in two stages.<n>First, we use an adaptive sample generation module to create updated samples by incorporating semantics from sample gradients.<n>Second, we employ a channel-wise dynamic distillation module to train student on these generated samples, guided by sample gradients and feature frequencies.
• Score: 53.278983063932706
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Knowledge Distillation (KD) offers a promising yet underexplored path for compressing large action recognition models. However, existing KD methods suffer from two key limitations: 1) reliance on fixed input samples leads to suboptimal feature alignment between the frozen teacher (larger model) and the learnable student (smaller model), and 2) applying a uniform distillation strength for all channels fails to account for their varying importance in capturing distinct knowledge (e.g., motion tempo or magnitude) across training epochs. This motivates us to develop an Adaptive Sample-aware Channel-wise Dynamic (ASCD) KD approach, which operates in two stages. First, we use an adaptive sample generation module to create updated samples by incorporating semantics from sample gradients, which are derived by minimizing a feature loss weighted by channel centroid frequency differences at each layer. Meanwhile, crucial motion-related details are preserved by applying a Gaussian mask to frequency features. Second, we employ a channel-wise dynamic distillation module to train student on these generated samples, guided by sample gradients and feature frequencies. For efficiency, samples are updated periodically rather than per epoch. Extensive experiments on three video benchmarks (UCF101, Kinetics-400, Something-Something-v2) and two image datasets (CIFAR-100, ImageNet) demonstrate the state-of-the-art performance of our method. Code is available at https://github.com/mlvccn/ASCD_KD_Action.

Related papers

• Dual-frequency Selected Knowledge Distillation with Statistical-based Sample Rectification for PolSAR Image Classification [11.844199868924505]
  The effect of regional consistency on classification information learning and the rational use of dual-frequency data are two main difficulties for dual-frequency collaborative classification.<n>A knowledge distillation network with statistical-based sample rectification (SKDNet-SSR) is proposed in this article.
  arXiv  Detail & Related papers  (2025-07-04T02:56:28Z)
• Smooth-Distill: A Self-distillation Framework for Multitask Learning with Wearable Sensor Data [0.0]
  This paper introduces Smooth-Distill, a novel self-distillation framework designed to simultaneously perform human activity recognition (HAR) and sensor placement detection.<n>Unlike conventional distillation methods that require separate teacher and student models, the proposed framework utilizes a smoothed, historical version of the model itself as the teacher.<n> Experimental results show that Smooth-Distill consistently outperforms alternative approaches across different evaluation scenarios.
  arXiv  Detail & Related papers  (2025-06-27T06:51:51Z)
• Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think [72.48325960659822]
  One main bottleneck in training large-scale diffusion models for generation lies in effectively learning these representations.<n>We study this by introducing a straightforward regularization called REPresentation Alignment (REPA), which aligns the projections of noisy input hidden states in denoising networks with clean image representations obtained from external, pretrained visual encoders.<n>The results are striking: our simple strategy yields significant improvements in both training efficiency and generation quality when applied to popular diffusion and flow-based transformers, such as DiTs and SiTs.
  arXiv  Detail & Related papers  (2024-10-09T14:34:53Z)
• Score-based Generative Models with Adaptive Momentum [40.84399531998246]
  We propose an adaptive momentum sampling method to accelerate the transforming process. We show that our method can produce more faithful images/graphs in small sampling steps with 2 to 5 times speed up.
  arXiv  Detail & Related papers  (2024-05-22T15:20:27Z)
• Adversarial Augmentation Training Makes Action Recognition Models More Robust to Realistic Video Distribution Shifts [12.818400676159953]
  Action recognition models often lack robustness when faced with natural distribution shifts between training and test data.<n>We propose two novel evaluation methods to assess model resilience to such distribution disparity.<n>We experimentally demonstrate the superior performance of the proposed adversarial augmentation approach over baselines across three state-of-the-art action recognition models.
  arXiv  Detail & Related papers  (2024-01-21T05:50:39Z)
• Value function estimation using conditional diffusion models for control [62.27184818047923]
  We propose a simple algorithm called Diffused Value Function (DVF) It learns a joint multi-step model of the environment-robot interaction dynamics using a diffusion model. We show how DVF can be used to efficiently capture the state visitation measure for multiple controllers.
  arXiv  Detail & Related papers  (2023-06-09T18:40:55Z)
• GCD-DDPM: A Generative Change Detection Model Based on Difference-Feature Guided DDPM [7.922421805234563]
  Deep learning methods have recently shown great promise in bitemporal change detection (CD) This work proposes a generative change detection model called GCD-DDPM to directly generate CD maps. Experiments on four high-resolution CD datasets confirm the superior performance of the proposed GCD-DDPM.
  arXiv  Detail & Related papers  (2023-06-06T05:51:50Z)
• 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)
• Activation to Saliency: Forming High-Quality Labels for Unsupervised Salient Object Detection [54.92703325989853]
  We propose a two-stage Activation-to-Saliency (A2S) framework that effectively generates high-quality saliency cues. No human annotations are involved in our framework during the whole training process. Our framework reports significant performance compared with existing USOD methods.
  arXiv  Detail & Related papers  (2021-12-07T11:54:06Z)
• Diffusion-Based Representation Learning [65.55681678004038]
  We augment the denoising score matching framework to enable representation learning without any supervised signal. In contrast, the introduced diffusion-based representation learning relies on a new formulation of the denoising score matching objective. Using the same approach, we propose to learn an infinite-dimensional latent code that achieves improvements of state-of-the-art models on semi-supervised image classification.
  arXiv  Detail & Related papers  (2021-05-29T09:26:02Z)
• Dynamic Sampling Networks for Efficient Action Recognition in Videos [43.51012099839094]
  We propose a new framework for action recognition in videos, called em Dynamic Sampling Networks (DSN) DSN is composed of a sampling module and a classification module, whose objective is to learn a sampling policy to on-the-fly select which clips to keep and train a clip-level classifier to perform action recognition based on these selected clips, respectively. We study different aspects of the DSN framework on four action recognition datasets: UCF101, HMDB51, THUMOS14, and ActivityNet v1.3.
  arXiv  Detail & Related papers  (2020-06-28T09:48:29Z)

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.