Multispectral pedestrian detection is an important task for many around-the-clock applications, since the visible and thermal modalities can provide complementary information especially under low light conditions. Most of the available multispectral pedestrian detectors are based on non-end-to-end detectors, while in this paper, we propose MultiSpectral pedestrian DEtection TRansformer (MS-DETR), an end-to-end multispectral pedestrian detector, which extends DETR into the field of multi-modal detection. MS-DETR consists of two modality-specific backbones and Transformer encoders, followed by a multi-modal Transformer decoder, and the visible and thermal features are fused in the multi-modal Transformer decoder. To well resist the misalignment between multi-modal images, we design a loosely coupled fusion strategy by sparsely sampling some keypoints from multi-modal features independently and fusing them with adaptively learned attention weights. Moreover, based on the insight that not only different modalities, but also different pedestrian instances tend to have different confidence scores to final detection, we further propose an instance-aware modality-balanced optimization strategy, which preserves visible and thermal decoder branches and aligns their predicted slots through an instance-wise dynamic loss. Our end-to-end MS-DETR shows superior performance on the challenging KAIST, CVC-14 and LLVIP benchmark datasets. The source code is available at https://github.com/YinghuiXing/MS-DETR .

翻译：暂无翻译