mlsanityData to 7 Oct 2026

Towards Robust Adaptive Object Detection under Noisy Annotations

arXiv 2204.02620 ↗First posted 6 Apr 2022cs.CVcited by 20

Not on the map. Why?

Abstract (arXiv)

Domain Adaptive Object Detection (DAOD) models a joint distribution of images and labels from an annotated source domain and learns a domain-invariant transformation to estimate the target labels with the given target domain images. Existing methods assume that the source domain labels are completely clean, yet large-scale datasets often contain error-prone annotations due to instance ambiguity, which may lead to a biased source distribution and severely degrade the performance of the domain adaptive detector de facto. In this paper, we represent the first effort to formulate noisy DAOD and propose a Noise Latent Transferability Exploration (NLTE) framework to address this issue. It is featured with 1) Potential Instance Mining (PIM), which leverages eligible proposals to recapture the miss-annotated instances from the background; 2) Morphable Graph Relation Module (MGRM), which models the adaptation feasibility and transition probability of noisy samples with relation matrices; 3) Entropy-Aware Gradient Reconcilement (EAGR), which incorporates the semantic information into the discrimination process and enforces the gradients provided by noisy and clean samples to be consistent towards learning domain-invariant representations. A thorough evaluation on benchmark DAOD datasets with noisy source annotations validates the effectiveness of NLTE. In particular, NLTE improves the mAP by 8.4% under 60% corrupted annotations and even approaches the ideal upper bound of training on a clean source dataset.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 46 of its 67 references that are in the map. First posted on arXiv 6 Apr 2022.

Builds on

46 of 67 references.

References · 46

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  3. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  4. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  5. 2014Conditional Generative Adversarial Netscited by 2,152
  6. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  7. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,053
  8. 2018On First-Order Meta-Learning Algorithmscited by 1,003
  9. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 994
  10. 2016Conditional Image Synthesis With Auxiliary Classifier GANscited by 562
  11. 2019Symmetric Cross Entropy for Robust Learning with Noisy Labelscited by 499
  12. 2017Regularizing Neural Networks by Penalizing Confident Output Distributionscited by 461
34 more
  1. 2018Domain Adaptive Faster R-CNN for Object Detection in the Wildcited by 442
  2. 2017Robust Loss Functions under Label Noise for Deep Neural Networkscited by 441
  3. 2017Semantic Foggy Scene Understanding with Synthetic Datacited by 401
  4. 2019How does Disagreement Help Generalization against Label Corruption?cited by 390
  5. 2019Unsupervised Label Noise Modeling and Loss Correctioncited by 327
  6. 2014Training Deep Neural Networks on Noisy Labels with Bootstrappingcited by 322
  7. 2018Strong-Weak Distribution Alignment for Adaptive Object Detectioncited by 269
  8. 2021Gradient Matching for Domain Generalizationcited by 258
  9. 2020Normalized Loss Functions for Deep Learning with Noisy Labelscited by 257
  10. 2020VarifocalNet: An IoU-aware Dense Object Detectorcited by 230
  11. 2018Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptationcited by 218
  12. 2019Deep learning with noisy labels: exploring techniques and remedies in medical image analysiscited by 173
  13. 2019Exploring Object Relation in Mean Teacher for Cross-Domain Detectioncited by 136
  14. 2018CurriculumNet: Weakly Supervised Learning from Large-Scale Web Imagescited by 126
  15. 2020Harmonizing Transferability and Discriminability for Adapting Object Detectorscited by 125
  16. 2020Deep Learning for LiDAR Point Clouds in Autonomous Driving: A Reviewcited by 114
  17. 2019Multi-adversarial Faster-RCNN for Unrestricted Object Detectioncited by 111
  18. 2020Cross-domain Detection via Graph-induced Prototype Alignmentcited by 109
  19. 2020Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detectorcited by 106
  20. 2021Provably End-to-end Label-Noise Learning without Anchor Pointscited by 97
  21. 2020Cross-domain Object Detection through Coarse-to-Fine Feature Adaptationcited by 82
  22. 2019Discriminative Adversarial Domain Adaptationcited by 74
  23. 2021Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularizationcited by 62
  24. 2020Spatial Attention Pyramid Network for Unsupervised Domain Adaptationcited by 56
  25. 2020Domain Adaptive Object Detection via Asymmetric Tri-way Faster-RCNNcited by 55
  26. 2021Vector-Decomposed Disentanglement for Domain-Invariant Object Detectioncited by 47
  27. 2021Learning with Noisy Labels via Sparse Regularizationcited by 38
  28. 2020Adaptive Object Detection with Dual Multi-Label Predictioncited by 26
  29. 2021Domain-Specific Suppression for Adaptive Object Detectioncited by 26
  30. 2020Towards Noise-resistant Object Detection with Noisy Annotationscited by 24
  31. 2021Synergizing between Self-Training and Adversarial Learning for Domain Adaptive Object Detectioncited by 24
  32. 2019Training Object Detectors With Noisy Datacited by 19
  33. 2019Empirical Upper Bound in Object Detection and Morecited by 12
  34. 2020Towards Accurate and Robust Domain Adaptation under Noisy Environmentscited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 2; 2024: 7; 2025: 6; 2026: 3.

20 papers.

Sort:

By area:

  1. 2025Large Self-Supervised Models Bridge the Gap in Domain Adaptive Object Detectioncited by 9
  2. 2022Combating noisy labels in object detection datasetscited by 7
  3. 2024GTP-4o: Modality-prompted Heterogeneous Graph Learning for Omni-modal Biomedical Representationcited by 7
  4. 2023Compensation Learning in Semantic Segmentationcited by 5
  5. 2022Extreme Image Transformations Affect Humans and Machines Differentlycited by 4
  6. 2023In-context Cross-Density Adaptation on Noisy Mammogram Abnormalities Detectioncited by 4
  7. 2024GLC++: Source-Free Universal Domain Adaptation through Global-Local Clustering and Contrastive Affinity Learningcited by 4
  8. 2024Domain Adaptive Detection of MAVs: A Benchmark and Noise Suppression Networkcited by 4
  9. 2025Diffusion Domain Teacher: Diffusion Guided Domain Adaptive Object Detectorcited by 4
  10. 2024Exploring Aleatoric Uncertainty in Object Detection via Vision Foundation Modelscited by 3
  11. 2025ConcealGS: Concealing Invisible Copyright Information in 3D Gaussian Splattingcited by 3
  12. 2024RobustFormer: Noise-Robust Pre-training for images and videoscited by 2
8 more
  1. 2024Universal Domain Adaptive Object Detection via Dual Probabilistic Alignmentcited by 2
  2. 2024Improving Object Detection via Local-global Contrastive Learningcited by 1
  3. 2025FMG-Det: Foundation Model Guided Robust Object Detectioncited by 0
  4. 2025De-Simplifying Pseudo Labels to Enhancing Domain Adaptive Object Detectioncited by 0
  5. 2025PAGen: Phase-guided Amplitude Generation for Domain-adaptive Object Detectioncited by 0
  6. 2026Combating Noisy Labels through Fostering Self- and Neighbor-Consistencycited by 0
  7. 2026Heterogeneous Model Fusion for Privacy-Aware Multi-Camera Surveillance via Synthetic Domain Adaptationcited by 0
  8. 2026Semantically Compatible Knowledge Distillation for Cross-Domain Object Detection with Vision Foundation Modelscited by 0