Causal Mode Multiplexer: A Novel Framework for Unbiased Multispectral Pedestrian Detection
This addresses a critical generalization issue in safety-critical pedestrian detection systems for day/night operations, though it is incremental as it builds on existing multispectral detection methods.
The paper tackles the modality bias problem in multispectral pedestrian detection, where detectors fail on data beyond statistical correlations like ROTX examples, by proposing a Causal Mode Multiplexer framework that learns causalities and shows strong generalization on existing and new datasets.
RGBT multispectral pedestrian detection has emerged as a promising solution for safety-critical applications that require day/night operations. However, the modality bias problem remains unsolved as multispectral pedestrian detectors learn the statistical bias in datasets. Specifically, datasets in multispectral pedestrian detection mainly distribute between ROTO (day) and RXTO (night) data; the majority of the pedestrian labels statistically co-occur with their thermal features. As a result, multispectral pedestrian detectors show poor generalization ability on examples beyond this statistical correlation, such as ROTX data. To address this problem, we propose a novel Causal Mode Multiplexer (CMM) framework that effectively learns the causalities between multispectral inputs and predictions. Moreover, we construct a new dataset (ROTX-MP) to evaluate modality bias in multispectral pedestrian detection. ROTX-MP mainly includes ROTX examples not presented in previous datasets. Extensive experiments demonstrate that our proposed CMM framework generalizes well on existing datasets (KAIST, CVC-14, FLIR) and the new ROTX-MP. We will release our new dataset to the public for future research.