SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Sep 11, 2026 · UTC

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

Read original source ↗ Open in workspace

recordType

paper

region

Global