Mutual-Supervised Feature Modulation Network for Occluded Pedestrian Detection

TL;DR

This paper introduces a novel Mutual-Supervised Feature Modulation network that improves occluded pedestrian detection by learning more complete features through a two-branch architecture and similarity loss, outperforming existing methods especially under heavy occlusion.

Contribution

The paper proposes a mutual-supervised feature modulation approach with a two-branch architecture and similarity loss to enhance occluded pedestrian detection.

Findings

Achieves superior performance on Caltech and CityPersons datasets.

Significantly improves detection accuracy under heavy occlusion.

Outperforms state-of-the-art methods in occlusion scenarios.

Abstract

State-of-the-art pedestrian detectors have achieved significant progress on non-occluded pedestrians, yet they are still struggling under heavy occlusions. The recent occlusion handling strategy of popular two-stage approaches is to build a two-branch architecture with the help of additional visible body annotations. Nonetheless, these methods still have some weaknesses. Either the two branches are trained independently with only score-level fusion, which cannot guarantee the detectors to learn robust enough pedestrian features. Or the attention mechanisms are exploited to only emphasize on the visible body features. However, the visible body features of heavily occluded pedestrians are concentrated on a relatively small area, which will easily cause missing detections. To address the above issues, we propose in this paper a novel Mutual-Supervised Feature Modulation (MSFM) network, to better handle occluded pedestrian detection. The key MSFM module in our network calculates the similarity loss of full body boxes and visible body boxes corresponding to the same pedestrian so that the full-body detector could learn more complete and robust pedestrian features with the assist of contextual features from the occluding parts. To facilitate the MSFM module, we also propose a novel two-branch architecture, consisting of a standard full body detection branch and an extra visible body classification branch. These two branches are trained in a mutual-supervised way with full body annotations and visible body annotations, respectively. To verify the effectiveness of our proposed method, extensive experiments are conducted on two challenging pedestrian datasets: Caltech and CityPersons, and our approach achieves superior performance compared to other state-of-the-art methods on both datasets, especially in heavy occlusion case.