IRIS Lab's (Prof. Hak Gu Kim) paper accepted to CVPR 2024 (AI Top-tier Conference)
관리자 │ 2024-02-28 HIT 33153 |
---|
Our paper of Immersive Reality and Intelligent Systems (IRIS) Lab is accepted to Conference on Computer Vision and Pattern Recognition (CVPR) 2024, Top Conference in AI & Computer Vision Title: Causal Mode Multiplexer: A Novel Framework for Unbiased Multispectral Pedestrian Detection Authors: Taeheon Kim, Sebin Shin, Youngjoon Yu, Hak Gu Kim, Yong Man Ro Abstract: 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. |
이전글 | IRIS Lab's (Prof. Hak Gu Kim) paper published in IEEE SPL (IF: 3.9) |
---|---|
다음글 | VI Lab's (Prof. Jongwon Choi) two papers accepted to CVPR 2024 (AI Top-tier Conf... |