# Learning from Noisy Anchors for One-stage Object Detection Source: [Learning from Noisy Anchors for One-stage Object Detection]() Collection index: [llms.txt]() Data updated: 2025-10-25T22:19:06.029Z Authors: Hengduo Li, Zuxuan Wu, Chen Zhu, Caiming Xiong, Richard Socher, Larry S. Davis Published: 2019-12-11T02:17:32.000Z ## Abstract State-of-the-art object detectors rely on regressing and classifying an extensive list of possible anchors, which are divided into positive and negative samples based on their intersection-over-union (IoU) with corresponding groundtruth objects. Such a harsh split conditioned on IoU results in binary labels that are potentially noisy and challenging for training. In this paper, we propose to mitigate noise incurred by imperfect label assignment such that the contributions of anchors are dynamically determined by a carefully constructed cleanliness score associated with each anchor. Exploring outputs from both regression and classification branches, the cleanliness scores, estimated without incurring any additional computational overhead, are used not only as soft labels to supervise the training of the classification branch but also sample re-weighting factors for improved localization and classification accuracy. We conduct extensive experiments on COCO, and demonstrate, among other things, the proposed approach steadily improves RetinaNet by ~2% with various backbones. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Object Detection on COCO v2017 (test-dev)](): Object Detection; COCO v2017 (test-dev); mAP: 44.1. - [Object Detection on COCO (test-dev)](): Object Detection; COCO (test-dev); mAP: 44.1. - [Object Detection on COCO 2017 (val)](): Object Detection; COCO 2017 (val); AP: 38. ## Original sources and implementation [Original paper]() [PDF]()