用少量样本精准计数密集小目标，定位更准
CoDi -- an exemplar-conditioned diffusion model for low-shot counting
- 基于扩散模型，用样本原型动态调整网络中间层
- 在FSC上少样本场景误差降低15%，新标杆
- 适合小样本、密集物体的精准计数任务
低样本物体计数旨在仅用少量或无标注样本的情况下估计图像中未见过物体的数量。现有方法在密集区域小物体计数上面临挑战：密度法虽能准确统计总数，但定位能力差；点检测法定位好，但预训练查询有限，在大数量物体时表现不佳，依赖采样和拼接等临时手段。本文提出CoDi，首个基于潜在扩散的低样本计数模型，生成高质量密度图，可通过非极大值抑制确定物体位置。核心创新是示例条件模块，将样本原型提取并适配到去噪网络中间层，实现精准定位。在FSC基准上，少样本、单样本和无参考场景下，相比当前最优方法分别降低15%、13%、10% MAE；在MCAC基准上，比顶尖方法降低38% MAE，刷新纪录。代码已开源。
原文摘要 · Abstract (English)
Low-shot object counting addresses estimating the number of previously unobserved objects in an image using only few or no annotated test-time exemplars. A considerable challenge for modern low-shot counters are dense regions with small objects. While total counts in such situations are typically well addressed by density-based counters, their usefulness is limited by poor localization capabilities. This is better addressed by point-detection-based counters, which are based on query-based detectors. However, due to limited number of pre-trained queries, they underperform on images with very large numbers of objects, and resort to ad-hoc techniques like upsampling and tiling. We propose CoDi, the first latent diffusion-based low-shot counter that produces high-quality density maps on which object locations can be determined by non-maxima suppression. Our core contribution is the new exemplar-based conditioning module that extracts and adjusts the object prototypes to the intermediate layers of the denoising network, leading to accurate object location estimation. On FSC benchmark, CoDi outperforms state-of-the-art by 15% MAE, 13% MAE and 10% MAE in the few-shot, one-shot, and reference-less scenarios, respectively, and sets a new state-of-the-art on MCAC benchmark by outperforming the top method by 38% MAE. The code is available at https://github.com/gsustar/CoDi
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。