Unlimited Knowledge Distillation for Action Recognition in the Dark

TL;DR

This paper introduces Unlimited Knowledge Distillation (UKD), a method that enables effective knowledge transfer for action recognition in dark videos without high GPU memory use, outperforming some existing models.

Contribution

The paper proposes UKD, a novel knowledge distillation approach that assembles knowledge from unlimited teacher models efficiently, overcoming memory constraints in video action recognition.

Findings

UKD enriches the network's learned knowledge.

Single stream network with UKD surpasses two-stream network.

Effective on ARID dataset.

Abstract

Dark videos often lose essential information, which causes the knowledge learned by networks is not enough to accurately recognize actions. Existing knowledge assembling methods require massive GPU memory to distill the knowledge from multiple teacher models into a student model. In action recognition, this drawback becomes serious due to much computation required by video process. Constrained by limited computation source, these approaches are infeasible. To address this issue, we propose an unlimited knowledge distillation (UKD) in this paper. Compared with existing knowledge assembling methods, our UKD can effectively assemble different knowledge without introducing high GPU memory consumption. Thus, the number of teaching models for distillation is unlimited. With our UKD, the network's learned knowledge can be remarkably enriched. Our experiments show that the single stream network distilled with our UKD even surpasses a two-stream network. Extensive experiments are conducted on the ARID dataset.