Papers › Multimodal Object Detection by Channel Switching and Spatial Attention

Multimodal Object Detection by Channel Switching and Spatial Attention

18 Jun 2023Conference on Computer Vision and Pattern Recognition (CVPR) 2023 6archive 2025-07-28

Yue Cao, Junchi Bin, Jozsef Hamari, Erik Blasch, Zheng Liu

Multimodal object detection has attracted great attention in recent years since the information specific to different modalities can complement each other and effectively improve the accuracy and stability of the detection model. However, compared to processing the inputs from a single modality, fusing information from multiple modalities can significantly increase the computational complexity of the model, thus impairing its efficiency. Therefore the multi-modal fusion module needs to be carefully designed to enhance the performance of the detection model while keeping the computational consumption low. In this paper, we propose a novel lightweight fusion module that can efficiently fuse the inputs from different modalities using channel switching and spatial attention (CSSA). The effectiveness and generalizability of the module are tested using two public multimodal datasets LLVIP and FLIR, both of which comprise paired infrared (IR) and visible (RGB) images. The experiments demonstrate that the proposed CSSA module can substantially improve the accuracy of multimodal object detection without consuming excessive computing resources.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Multispectral Object DetectionObject DetectionPedestrian Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multispectral Object Detection FLIR CSSA mAP 41.3% #8 of 18 Archive leaderboard report
Multispectral Object Detection FLIR CSSA mAP50 79.2% #8 of 18 Archive leaderboard report
Multispectral Object Detection FLIR ProbEn mAP 37.9% #10 of 18 Archive leaderboard report
Multispectral Object Detection FLIR ProbEn mAP50 75.5% #10 of 18 Archive leaderboard report
Multispectral Object Detection FLIR GAFF mAP 37.4% #11 of 18 Archive leaderboard report
Multispectral Object Detection FLIR GAFF mAP50 74.6% #11 of 18 Archive leaderboard report
Multispectral Object Detection FLIR Halfway Fusion mAP 35.8% #18 of 18 Archive leaderboard report
Pedestrian Detection LLVIP CSSA AP 0.592 #8 of 15 Archive leaderboard report
Pedestrian Detection LLVIP GAFF AP 0.558 #9 of 15 Archive leaderboard report
Pedestrian Detection LLVIP Halfway Fusion AP 0.551 #10 of 15 Archive leaderboard report
Pedestrian Detection LLVIP ProbEn AP 0.515 #12 of 15 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections