Papers › Cross-Modality Fusion Transformer for Multispectral Object Detection

Cross-Modality Fusion Transformer for Multispectral Object Detection

30 Oct 2021arXiv:2111.00273archive 2025-07-28

Fang Qingyun, Han Dapeng, Wang Zhaokui

Multispectral image pairs can provide the combined information, making object detection applications more reliable and robust in the open world. To fully exploit the different modalities, we present a simple yet effective cross-modality feature fusion approach, named Cross-Modality Fusion Transformer (CFT) in this paper. Unlike prior CNNs-based works, guided by the transformer scheme, our network learns long-range dependencies and integrates global contextual information in the feature extraction stage. More importantly, by leveraging the self attention of the transformer, the network can naturally carry out simultaneous intra-modality and inter-modality fusion, and robustly capture the latent interactions between RGB and Thermal domains, thereby significantly improving the performance of multispectral object detection. Extensive experiments and ablation studies on multiple datasets demonstrate that our approach is effective and achieves state-of-the-art detection performance. Our code and models are available at https://github.com/DocF/multispectral-object-detection.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

docf/multispectral-object-detection officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

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

Tasks

Multispectral Object DetectionObjectObject DetectionPedestrian Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multispectral Object Detection FLIR CFT mAP50 77.7% #9 of 18 Archive leaderboard report
Multispectral Object Detection FLIR YOLOv5 (T) mAP50 73.9% #12 of 18 Archive leaderboard report
Multispectral Object Detection FLIR YOLOv5 (RGB) mAP50 67.8% #17 of 18 Archive leaderboard report
Multispectral Object Detection LLVIP CFT mAP50 97.5 #1 of 1 Archive leaderboard report
Pedestrian Detection CVC14 CFT AP50 78.2 #1 of 2 Archive leaderboard report
Pedestrian Detection DVTOD CFT mAP 82.7 #2 of 8 Archive leaderboard report
Pedestrian Detection LLVIP CFT AP 0.636 #4 of 15 Archive leaderboard report
Pedestrian Detection LLVIP CFT log average miss rate 5.40% #4 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.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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