mlsanityData to 7 Oct 2026

A Benchmark of Long-tailed Instance Segmentation with Noisy Labels

arXiv 2211.13435 ↗First posted 24 Nov 2022cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

In this paper, we consider the instance segmentation task on a long-tailed dataset, which contains label noise, i.e., some of the annotations are incorrect. There are two main reasons making this case realistic. First, datasets collected from real world usually obey a long-tailed distribution. Second, for instance segmentation datasets, as there are many instances in one image and some of them are tiny, it is easier to introduce noise into the annotations. Specifically, we propose a new dataset, which is a large vocabulary long-tailed dataset containing label noise for instance segmentation. Furthermore, we evaluate previous proposed instance segmentation algorithms on this dataset. The results indicate that the noise in the training dataset will hamper the model in learning rare categories and decrease the overall performance, and inspire us to explore more effective approaches to address this practical challenge. The code and dataset are available in https://github.com/GuanlinLee/Noisy-LVIS.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 41 of its 51 references that are in the map. First posted on arXiv 24 Nov 2022.

Builds on

41 of 51 references.

References · 41

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  6. 2017Mask R-CNNcited by 7,259
  7. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  8. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  9. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  10. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,483
  11. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
  12. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
29 more
  1. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,239
  2. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,215
  3. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,053
  4. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 994
  5. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 987
  6. 2017Focal Loss for Dense Object Detectioncited by 749
  7. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 691
  8. 2016Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approachcited by 663
  9. 2020Long-tail learning via logit adjustmentcited by 605
  10. 2020Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentationcited by 595
  11. 2020Learning from Noisy Labels with Deep Neural Networks: A Surveycited by 580
  12. 2017Robust Loss Functions under Label Noise for Deep Neural Networkscited by 441
  13. 2020Balanced Meta-Softmax for Long-Tailed Visual Recognitioncited by 397
  14. 2014Training Deep Neural Networks on Noisy Labels with Bootstrappingcited by 322
  15. 2020Equalization Loss for Long-Tailed Object Recognitioncited by 285
  16. 2017WebVision Database: Visual Learning and Understanding from Web Datacited by 262
  17. 2020Does label smoothing mitigate label noise?cited by 204
  18. 2020Seesaw Loss for Long-Tailed Instance Segmentationcited by 146
  19. 2020The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance Segmentationcited by 108
  20. 2020Equalization Loss v2: A New Gradient Balance Approach for Long-tailed Object Detectioncited by 99
  21. 2021FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentationcited by 76
  22. 2019Robust Inference via Generative Classifiers for Handling Noisy Labelscited by 67
  23. 2020Learning to Segment the Tailcited by 54
  24. 2018Deep Bilevel Learningcited by 48
  25. 2014Training Convolutional Networks with Noisy Labelscited by 47
  26. 2021Robust Long-Tailed Learning under Label Noisecited by 35
  27. 2021DropLoss for Long-Tail Instance Segmentationcited by 32
  28. 2021Learning From Long-Tailed Data With Noisy Labelscited by 17
  29. 2022Long-tailed Instance Segmentation using Gumbel Optimized Losscited by 12

Built on by

Not cited yet.