Search and Detect: Training-Free Long Tail Object Detection via Web-Image Retrieval

Mankeerat Sidhu, Hetarth Chopra, Ansel Blume, Jeonghwan Kim, Revanth Gangi Reddy, Heng Ji; Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR), 2025, pp. 15129-15138

Abstract


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 16.81% mAP improvement on ODinW and 59.85% 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.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sidhu_2025_CVPR, author = {Sidhu, Mankeerat and Chopra, Hetarth and Blume, Ansel and Kim, Jeonghwan and Reddy, Revanth Gangi and Ji, Heng}, title = {Search and Detect: Training-Free Long Tail Object Detection via Web-Image Retrieval}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR)}, month = {June}, year = {2025}, pages = {15129-15138} }