# Learning from Noisy Anchors for One-stage Object Detection

arXiv: https://arxiv.org/abs/1912.05086 · HTML: https://mlsanity.com/paper/1912.05086/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Dec 2019.

## Built on by (most cited first, 30 of 35)

- [TOOD: Task-aligned One-stage Object Detection](https://mlsanity.com/paper/2108.07755/) (2021)
- [OTA: Optimal Transport Assignment for Object Detection](https://mlsanity.com/paper/2103.14259/) (2021)
- [Efficient DETR: Improving End-to-End Object Detector with Dense Prior](https://mlsanity.com/paper/2104.01318/) (2021)
- [Oriented RepPoints for Aerial Object Detection](https://mlsanity.com/paper/2105.11111/) (2021)
- [UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learning](https://mlsanity.com/paper/2203.14542/) (2022)
- [Detecting tiny objects in aerial images: A normalized Wasserstein distance and a new benchmark](https://mlsanity.com/paper/2206.13996/) (2022)
- [Rethinking Pseudo Labels for Semi-Supervised Object Detection](https://mlsanity.com/paper/2106.00168/) (2021)
- [A Dual Weighting Label Assignment Scheme for Object Detection](https://mlsanity.com/paper/2203.09730/) (2022)
- [Visual Distant Supervision for Scene Graph Generation](https://mlsanity.com/paper/2103.15365/) (2021)
- [Detection Hub: Unifying Object Detection Datasets via Query Adaptation on Language Embedding](https://mlsanity.com/paper/2206.03484/) (2022)
- [LEOD: Label-Efficient Object Detection for Event Cameras](https://mlsanity.com/paper/2311.17286/) (2023)
- [Object Detection with Transformers: A Review](https://mlsanity.com/paper/2306.04670/) (2023)
- [Alpha-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression](https://mlsanity.com/paper/2110.13675/) (2021)
- [Improving Object Detection by Label Assignment Distillation](https://mlsanity.com/paper/2108.10520/) (2021)
- [Identifying Label Errors in Object Detection Datasets by Loss Inspection](https://mlsanity.com/paper/2303.06999/) (2023)
- [Solve the Puzzle of Instance Segmentation in Videos: A Weakly Supervised Framework with Spatio-Temporal Collaboration](https://mlsanity.com/paper/2212.07592/) (2022)
- [Mutual Supervision for Dense Object Detection](https://mlsanity.com/paper/2109.05986/) (2021)
- [Salvage of Supervision in Weakly Supervised Object Detection](https://mlsanity.com/paper/2106.04073/) (2021)
- [Recent Few-Shot Object Detection Algorithms: A Survey with Performance Comparison](https://mlsanity.com/paper/2203.14205/) (2022)
- [LLA: Loss-aware Label Assignment for Dense Pedestrian Detection](https://mlsanity.com/paper/2101.04307/) (2021)
- [Label Convergence: Defining an Upper Performance Bound in Object Recognition through Contradictory Annotations](https://mlsanity.com/paper/2409.09412/) (2024)
- [Mask-aware IoU for Anchor Assignment in Real-time Instance Segmentation](https://mlsanity.com/paper/2110.09734/) (2021)
- [Revisiting AP Loss for Dense Object Detection: Adaptive Ranking Pair Selection](https://mlsanity.com/paper/2207.12042/) (2022)
- [Revisiting the Loss Weight Adjustment in Object Detection](https://mlsanity.com/paper/2103.09488/) (2021)
- [A Flying Bird Object Detection Method for Surveillance Video](https://mlsanity.com/paper/2401.03749/) (2024)
- [Leveraging Anchor-based LiDAR 3D Object Detection via Point Assisted Sample Selection](https://mlsanity.com/paper/2403.01978/) (2024)
- [Mitigating the Impact of Prominent Position Shift in Drone-based RGBT Object Detection](https://mlsanity.com/paper/2502.09311/) (2025)
- [Density-based Object Detection in Crowded Scenes](https://mlsanity.com/paper/2504.09819/) (2025)
- [Impact of Localization Errors on Label Quality for Online HD Map Construction](https://mlsanity.com/paper/2603.03452/) (2026)
- [Toward Minimal Misalignment at Minimal Cost in One-Stage and Anchor-Free Object Detection](https://mlsanity.com/paper/2112.08902/) (2021)

## Abstract (arXiv)

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.