# Towards Noise-resistant Object Detection with Noisy Annotations

arXiv: https://arxiv.org/abs/2003.01285 · HTML: https://mlsanity.com/paper/2003.01285/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Mar 2020.

## Built on by (most cited first, 25 of 25)

- [Sum of Ranked Range Loss for Supervised Learning](https://mlsanity.com/paper/2106.03300/) (2021)
- [Towards Robust Adaptive Object Detection under Noisy Annotations](https://mlsanity.com/paper/2204.02620/) (2022)
- [Robust Object Detection With Inaccurate Bounding Boxes](https://mlsanity.com/paper/2207.09697/) (2022)
- [Alpha-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression](https://mlsanity.com/paper/2110.13675/) (2021)
- [SparseDet: Improving Sparsely Annotated Object Detection with Pseudo-positive Mining](https://mlsanity.com/paper/2201.04620/) (2022)
- [Evaluating Multi-label Classifiers with Noisy Labels](https://mlsanity.com/paper/2102.08427/) (2021)
- [Noisy Annotation Refinement for Object Detection](https://mlsanity.com/paper/2110.10456/) (2021)
- [Spatial Self-Distillation for Object Detection with Inaccurate Bounding Boxes](https://mlsanity.com/paper/2307.12101/) (2023)
- [Combating noisy labels in object detection datasets](https://mlsanity.com/paper/2211.13993/) (2022)
- [Label Convergence: Defining an Upper Performance Bound in Object Recognition through Contradictory Annotations](https://mlsanity.com/paper/2409.09412/) (2024)
- [Robust Tiny Object Detection in Aerial Images amidst Label Noise](https://mlsanity.com/paper/2401.08056/) (2024)
- [Sample Selection via Contrastive Fragmentation for Noisy Label Regression](https://mlsanity.com/paper/2502.17771/) (2025)
- [Distribution-Aware Calibration for Object Detection with Noisy Bounding Boxes](https://mlsanity.com/paper/2308.12017/) (2023)
- [Universal Noise Annotation: Unveiling the Impact of Noisy annotation on Object Detection](https://mlsanity.com/paper/2312.13822/) (2023)
- [NBBOX: Noisy Bounding Box Improves Remote Sensing Object Detection](https://mlsanity.com/paper/2409.09424/) (2024)
- [Multi-Label Gold Asymmetric Loss Correction with Single-Label Regulators](https://mlsanity.com/paper/2108.02032/) (2021)
- [Soft-labeling Strategies for Rapid Sub-Typing](https://mlsanity.com/paper/2209.12684/) (2022)
- [Robust Object Detection in Remote Sensing Imagery with Noisy and Sparse Geo-Annotations (Full Version)](https://mlsanity.com/paper/2210.12989/) (2022)
- [Dynamic Loss Decay based Robust Oriented Object Detection on Remote Sensing Images with Noisy Labels](https://mlsanity.com/paper/2405.09024/) (2024)
- [Rethinking Annotation for Object Detection: Is Annotating Small-size Instances Worth Its Cost?](https://mlsanity.com/paper/2412.05611/) (2024)
- [Benchmarking Deep Learning-Based Object Detection Models on Feature Deficient Astrophotography Imagery Dataset](https://mlsanity.com/paper/2508.06537/) (2025)
- [FMG-Det: Foundation Model Guided Robust Object Detection](https://mlsanity.com/paper/2505.23726/) (2025)
- [Noise-Robust Tiny Object Localization with Flows](https://mlsanity.com/paper/2601.00617/) (2026)
- [Active Label Cleaning for Reliable Detection of Electron Dense Deposits in Transmission Electron Microscopy Images](https://mlsanity.com/paper/2602.05250/) (2026)
- [KαLOS finds Consensus: A Meta-Algorithm for Evaluating Inter-Annotator Agreement in Complex Vision Tasks](https://mlsanity.com/paper/2603.27197/) (2026)

## Abstract (arXiv)

Training deep object detectors requires significant amount of human-annotated images with accurate object labels and bounding box coordinates, which are extremely expensive to acquire. Noisy annotations are much more easily accessible, but they could be detrimental for learning. We address the challenging problem of training object detectors with noisy annotations, where the noise contains a mixture of label noise and bounding box noise. We propose a learning framework which jointly optimizes object labels, bounding box coordinates, and model parameters by performing alternating noise correction and model training. To disentangle label noise and bounding box noise, we propose a two-step noise correction method. The first step performs class-agnostic bounding box correction by minimizing classifier discrepancy and maximizing region objectness. The second step distils knowledge from dual detection heads for soft label correction and class-specific bounding box refinement. We conduct experiments on PASCAL VOC and MS-COCO dataset with both synthetic noise and machine-generated noise. Our method achieves state-of-the-art performance by effectively cleaning both label noise and bounding box noise. Code to reproduce all results will be released.