Label-Guided Knowledge Distillation for 3D-CNNs in Action Recognition

2026-09-11

AI Summary

为解决3D-CNN在动作识别中特征蒸馏忽视时间维度差异的问题，提出标签引导的知识蒸馏方法LGKD，通过样本级和类别级蒸馏增强学生模型性能。

Abstract

As a key model compression technique, knowledge distillation aims to transfer knowledge from a high-capacity teacher model to a lightweight student model for enhancing the latter's performance. In this work, we reviewed the feature knowledge distillation for 3D-CNNs and observed that most feature distillation methods in video analysis are simple adaptations of those used in image analysis, often neglecting the differences of video features in the temporal dimension. To address this issue, we proposed Label-Guided Knowledge Distillation (LGKD) to guide the distillation of student model features using ground truth labels. Our method entails two components: sample-wise distillation and class-wise distillation, enabling the student model to learn feature representation of the teacher model at two levels. Sample-wise distillation utilizes label information and the teacher's probability distribution to guide the learning of features that significantly impact temporal accuracy while mitigating noise. Meanwhile, class-wise feature distillation employs a prototype network to further capture the relational knowledge among samples within the same category, enhancing the student's ability to learn higher-dimensional semantic information and improving model generalization. To demonstrate the effectiveness and superiority of our method, we conducted comprehensive experiments on two benchmark action recognition datasets, UCF101 and HMDB51, achieving competitive results.

Problem

• knowledge distillation
• 3D-CNNs
• action recognition
• temporal dimension
• feature representation

Innovation

• Label-Guided Knowledge Distillation
• 3D-CNNs
• Action Recognition
• Sample-wise Distillation
• Class-wise Distillation