用生成式流模型统一目标检测，速度更快、精度更高。
FlowDet: Unifying Object Detection and Generative Transport Flows
- 将检测问题重新定义为生成式流传输，路径更直更高效。
- 在COCO和LVIS上分别提升3.6%和4.2%的检测精度。
- 适合追求高召回率与推理效率的研究者或工业应用。
我们提出FlowDet，首个基于现代条件流匹配技术的目标检测框架。该工作源于DiffusionDet，后者首次将检测建模为边界框空间中的生成去噪问题。FlowDet在此基础上进行推广，将其扩展至更广泛的生成式传输问题，同时保持无需重训练即可调整框数和推理步数的能力。与扩散模型带来的弯曲随机路径不同，FlowDet学习更简单、更直接的路径，使得检测性能随推理步数增加而更快提升。实验表明，该方法在多种骨干网络和数据集上均优于基于扩散的检测系统及非生成式基线。尤其在召回率受限条件下，可有效凸显生成式传输的优势而不依赖大量候选框。在COCO和LVIS数据集上，分别实现+3.6% AP和+4.2% AP$_{rare}$的提升。
原文摘要 · Abstract (English)
We present FlowDet, the first formulation of object detection using modern Conditional Flow Matching techniques. This work follows from DiffusionDet, which originally framed detection as a generative denoising problem in the bounding box space via diffusion. We revisit and generalise this formulation to a broader class of generative transport problems, while maintaining the ability to vary the number of boxes and inference steps without re-training. In contrast to the curved stochastic transport paths induced by diffusion, FlowDet learns simpler and straighter paths resulting in faster scaling of detection performance as the number of inference steps grows. We find that this reformulation enables us to outperform diffusion based detection systems (as well as non-generative baselines) across a wide range of experiments, including various precision/recall operating points using multiple feature backbones and datasets. In particular, when evaluating under recall-constrained settings, we can highlight the effects of the generative transport without over-compensating with large numbers of proposals. This provides gains of up to +3.6% AP and +4.2% AP$_{rare}$ over DiffusionDet on the COCO and LVIS datasets, 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。