用网络图片检索实现无需训练的长尾目标检测，效果显著提升。
Search and Detect: Training-Free Long Tail Object Detection via Web-Image Retrieval
- 通过网络检索正负样本图像，构建输入加权查询进行检测。
- 在ODinW上提升48.7% mAP，LVIS上提升59.1% mAP。
- 无需训练和标注，适合开放词汇检测与资源受限场景。
本文提出SearchDet，一种无需训练的长尾目标检测框架，显著提升开放词汇目标检测性能。SearchDet通过检索目标物体的正负样本图像，对这些图像进行嵌入，并生成基于输入图像加权的查询，用于在图像中检测目标概念。该方法简单且无需训练，在ODinW上相比GroundingDINO等先进模型提升超过48.7% mAP，LVIS上提升59.1% mAP。此外，我们表明基于网络检索样本进行检测的方法对样本变化具有稳定性，为消除昂贵的数据标注和训练流程提供了可行路径。
原文摘要 · Abstract (English)
In this paper, we introduce SearchDet, a training-free long-tail object detection framework that significantly enhances open-vocabulary object detection performance. SearchDet retrieves a set of positive and negative images of an object to ground, embeds these images, and computes an input image-weighted query which is used to detect the desired concept in the image. Our proposed method is simple and training-free, yet achieves over 48.7% mAP improvement on ODinW and 59.1% mAP improvement on LVIS compared to state-of-the-art models such as GroundingDINO. We further show that our approach of basing object detection on a set of Web-retrieved exemplars is stable with respect to variations in the exemplars, suggesting a path towards eliminating costly data annotation and training procedures.
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。