DL-KDD: Dual-Light Knowledge Distillation for Action Recognition in the Dark

TL;DR

This paper introduces DL-KDD, a teacher-student framework that improves dark video action recognition by learning from both original and enhanced videos during training, without extra inference costs.

Contribution

The novel DL-KDD framework enables effective dark video action recognition through knowledge distillation, avoiding additional inference complexity and outperforming existing methods.

Findings

Outperforms state-of-the-art on ARID, ARID V1.5, Dark-48 datasets

Achieves up to 4.18% improvement on Dark-48

Validates effectiveness of knowledge distillation in dark video recognition

Abstract

Human action recognition in dark videos is a challenging task for computer vision. Recent research focuses on applying dark enhancement methods to improve the visibility of the video. However, such video processing results in the loss of critical information in the original (un-enhanced) video. Conversely, traditional two-stream methods are capable of learning information from both original and processed videos, but it can lead to a significant increase in the computational cost during the inference phase in the task of video classification. To address these challenges, we propose a novel teacher-student video classification framework, named Dual-Light KnowleDge Distillation for Action Recognition in the Dark (DL-KDD). This framework enables the model to learn from both original and enhanced video without introducing additional computational cost during inference. Specifically, DL-KDD utilizes the strategy of knowledge distillation during training. The teacher model is trained with enhanced video, and the student model is trained with both the original video and the soft target generated by the teacher model. This teacher-student framework allows the student model to predict action using only the original input video during inference. In our experiments, the proposed DL-KDD framework outperforms state-of-the-art methods on the ARID, ARID V1.5, and Dark-48 datasets. We achieve the best performance on each dataset and up to a 4.18% improvement on Dark-48, using only original video inputs, thus avoiding the use of two-stream framework or enhancement modules for inference. We further validate the effectiveness of the distillation strategy in ablative experiments. The results highlight the advantages of our knowledge distillation framework in dark human action recognition.