mlsanityData to 7 Oct 2026

Noise-Robust Tiny Object Localization with Flows

arXiv 2601.00617 ↗First posted 2 Jan 2026cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Despite significant advances in generic object detection, a persistent performance gap remains for tiny objects compared to normal-scale objects. We demonstrate that tiny objects are highly sensitive to annotation noise, where optimizing strict localization objectives risks noise overfitting. To address this, we propose Tiny Object Localization with Flows (TOLF), a noise-robust localization framework leveraging normalizing flows for flexible error modeling and uncertainty-guided optimization. Our method captures complex, non-Gaussian prediction distributions through flow-based error modeling, enabling robust learning under noisy supervision. An uncertainty-aware gradient modulation mechanism further suppresses learning from high-uncertainty, noise-prone samples, mitigating overfitting while stabilizing training. Extensive experiments across three datasets validate our approach's effectiveness. Especially, TOLF boosts the DINO baseline by 1.2% AP on the AI-TOD dataset.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 49 of its 62 references that are in the map. First posted on arXiv 2 Jan 2026.

Builds on

49 of 62 references.

References · 49

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2020End-to-End Object Detection with Transformerscited by 7,384
  5. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  6. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  7. 2015Fast R-CNNcited by 2,930
  8. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  9. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  10. 2016Density estimation using Real NVPcited by 2,029
  11. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  12. 2022DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detectioncited by 1,306
37 more
  1. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  2. 2018Path Aggregation Network for Instance Segmentationcited by 796
  3. 2019CenterNet: Keypoint Triplets for Object Detectioncited by 654
  4. 2017DOTA: A Large-scale Dataset for Object Detection in Aerial Imagescited by 622
  5. 2019Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selectioncited by 539
  6. 2020Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detectioncited by 408
  7. 2020DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolutioncited by 222
  8. 2019Scale-Aware Trident Networks for Object Detectioncited by 159
  9. 2020Probabilistic Anchor Assignment with IoU Prediction for Object Detectioncited by 150
  10. 2018Bounding Box Regression with Uncertainty for Accurate Object Detectioncited by 143
  11. 2021Human Pose Regression with Residual Log-likelihood Estimationcited by 131
  12. 2017An Analysis of Scale Invariance in Object Detection - SNIPcited by 119
  13. 2020AutoAssign: Differentiable Label Assignment for Dense Object Detectioncited by 100
  14. 2014Convolutional Neural Networks at Constrained Time Costcited by 81
  15. 2017Perceptual Generative Adversarial Networks for Small Object Detectioncited by 76
  16. 2019Augmentation for small object detectioncited by 73
  17. 2021QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detectioncited by 70
  18. 2019Scale Match for Tiny Person Detectioncited by 61
  19. 2022Detecting tiny objects in aerial images: A normalized Wasserstein distance and a new benchmarkcited by 56
  20. 2021A Normalized Gaussian Wasserstein Distance for Tiny Object Detectioncited by 52
  21. 2022RFLA: Gaussian Receptive Field based Label Assignment for Tiny Object Detectioncited by 51
  22. 2023Dynamic Coarse-to-Fine Learning for Oriented Tiny Object Detectioncited by 43
  23. 2023Adaptive Sparse Convolutional Networks with Global Context Enhancement for Faster Object Detection on Drone Imagescited by 41
  24. 2022Positive-incentive Noisecited by 39
  25. 2023Variational Positive-incentive Noise: How Noise Benefits Modelscited by 38
  26. 2024Enhance Vision-Language Alignment with Noisecited by 34
  27. 2024Data Augmentation of Contrastive Learning is Estimating Positive-incentive Noisecited by 25
  28. 2020Towards Noise-resistant Object Detection with Noisy Annotationscited by 24
  29. 2022Robust Object Detection With Inaccurate Bounding Boxescited by 20
  30. 2019Training Object Detectors With Noisy Datacited by 19
  31. 2025Learn Beneficial Noise as Graph Augmentationcited by 15
  32. 2025Mixture of Noise for Pre-Trained Model-Based Class-Incremental Learningcited by 14
  33. 2024Visible and Clear: Finding Tiny Objects in Difference Mapcited by 9
  34. 2023Dynamics-Aware Loss for Learning with Label Noisecited by 8
  35. 2025HieraTok: Multi-Scale Visual Tokenizer Improves Image Reconstruction and Generationcited by 7
  36. 2023Uncertainty-Aware Gradient Stabilization for Small Object Detectioncited by 2
  37. 20252D Gaussians Meet Visual Tokenizercited by 1

Built on by

Not cited yet.