用可微分的分数匹配改进目标检测，提升小物体和密集场景表现。
Fractional Correspondence Framework in Detection Transformer
- 引入可微分的运输计划，实现软性分数匹配而非严格一一对应。
- 在MS-COCO上比Deform-DETR高3.8% mAP，比DINO-DETR高1.7% mAP。
- 适合处理物体密度不均、小目标漏检等问题的检测任务。
检测变压器（DETR）通过引入匈牙利算法，显著简化了目标检测中的匹配过程。该算法在训练时实现了预测边界框与真实标注之间最优的一一匹配。然而，这种严格的匹配机制未能考虑物体密度和分布的差异，导致对应关系不佳，如同一物体多次检测或遗漏小物体。为此，我们提出正则化运输计划（RTP）。RTP引入了一种灵活的匹配策略，通过可微分的Sinkhorn算法捕捉预测与真实标注之间的对齐代价，实现软性、分数化的匹配而非严格的一一对应。该方法有效提升了模型对不同物体密度和分布的适应能力。在MS-COCO和VOC基准上的广泛评估表明，RTP-DETR性能优于Deform-DETR和近期提出的DINO-DETR，mAP分别提升3.8%和1.7%。
原文摘要 · Abstract (English)
The Detection Transformer (DETR), by incorporating the Hungarian algorithm, has significantly simplified the matching process in object detection tasks. This algorithm facilitates optimal one-to-one matching of predicted bounding boxes to ground-truth annotations during training. While effective, this strict matching process does not inherently account for the varying densities and distributions of objects, leading to suboptimal correspondences such as failing to handle multiple detections of the same object or missing small objects. To address this, we propose the Regularized Transport Plan (RTP). RTP introduces a flexible matching strategy that captures the cost of aligning predictions with ground truths to find the most accurate correspondences between these sets. By utilizing the differentiable Sinkhorn algorithm, RTP allows for soft, fractional matching rather than strict one-to-one assignments. This approach enhances the model's capability to manage varying object densities and distributions effectively. Our extensive evaluations on the MS-COCO and VOC benchmarks demonstrate the effectiveness of our approach. RTP-DETR, surpassing the performance of the Deform-DETR and the recently introduced DINO-DETR, achieving absolute gains in mAP of +3.8% and +1.7%, respectively.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。