Label-Guided Knowledge Distillation for 3D-CNNs in Action Recognition
LGKD uses ground-truth labels to guide feature distillation for 3D-CNNs, combining sample-wise and class-wise distillation for action recognition.
The paper proposes Label-Guided Knowledge Distillation (LGKD) for 3D-CNNs, noting that most video feature distillation methods are simple adaptations of image techniques that neglect temporal-dimension differences. LGKD combines sample-wise distillation, which uses label information and the teacher's probability distribution to guide features impacting temporal accuracy, with class-wise distillation employing a prototype network to capture relational knowledge among same-category samples. Experiments on the UCF101 and HMDB51 action recognition benchmarks achieve competitive results.
- Addresses temporal-dimension gaps in image-derived video distillation methods
- Sample-wise distillation uses labels and teacher probabilities to guide features
- Class-wise distillation uses a prototype network for relational knowledge
- Competitive results on UCF101 and HMDB51 benchmarks
Full article197 words · extracted from arxiv.org · click to collapse
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.
Text extracted automatically; images, tables and formatting may be missing. Original: https://arxiv.org/abs/2609.13024