SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.01300 · CVPR · 2024

Causal Mode Multiplexer: A Novel Framework for Unbiased Multispectral Pedestrian Detection

Yong Ro, Taeheon Kim, Hak Gu, Youngjoon Yu, Sebin Shin

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 4 functions out of this paper's own repositories and ran 0 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
ssbin0914/Causal-Mode-Multiplexer canonical 0 of 4
FunctionStatusWhere it lives
get_imdb Not yet run ssbin0914/Causal-Mode-Multiplexer/lib/datasets/factory.py
code served (permissive licence) · get_code("3be9228820b46ef3")
unique_boxes Not yet run ssbin0914/Causal-Mode-Multiplexer/lib/datasets/ds_utils.py
code served (permissive licence) · get_code("8a015c012f507631")
xywh_to_xyxy Not yet run ssbin0914/Causal-Mode-Multiplexer/lib/datasets/ds_utils.py
code served (permissive licence) · get_code("d3e019b11b709edb")
xyxy_to_xywh Not yet run ssbin0914/Causal-Mode-Multiplexer/lib/datasets/ds_utils.py
code served (permissive licence) · get_code("a832e5017f504280")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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 1 (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. Our code and dataset are available at: https://github.com/ssbin0914/Causal-Mode-Multiplexer.git. * Equally contributed. † Corresponding author. 1 R⋆T⋆ refers to the visibility (O/X) in each modality. Generally, ROTO refers to daytime images, and RXTO refers to nighttime images. ROTX refers to daytime images in obscured situations.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2403.01300")
get_code_for_paper("2403.01300")
have("2403.01300")

Connect an agent — have() is free.