mlsanityData to 14 Oct 2026

Multi-label Classification with Partial Annotations using Class-aware Selective Loss

arXiv 2110.10955 ↗First posted 21 Oct 2021cs.CVcited by 25

Not on the map. Why?

Abstract (arXiv)

Large-scale multi-label classification datasets are commonly, and perhaps inevitably, partially annotated. That is, only a small subset of labels are annotated per sample. Different methods for handling the missing labels induce different properties on the model and impact its accuracy. In this work, we analyze the partial labeling problem, then propose a solution based on two key ideas. First, un-annotated labels should be treated selectively according to two probability quantities: the class distribution in the overall dataset and the specific label likelihood for a given data sample. We propose to estimate the class distribution using a dedicated temporary model, and we show its improved efficiency over a naive estimation computed using the dataset's partial annotations. Second, during the training of the target model, we emphasize the contribution of annotated labels over originally un-annotated labels by using a dedicated asymmetric loss. With our novel approach, we achieve state-of-the-art results on OpenImages dataset (e.g. reaching 87.3 mAP on V6). In addition, experiments conducted on LVIS and simulated-COCO demonstrate the effectiveness of our approach. Code is available at https://github.com/Alibaba-MIIL/PartialLabelingCSL.

Key facts. Cited by 25 papers in the map (data through 14 Oct 2026). Builds on 27 of its 33 references that are in the map. First posted on arXiv 21 Oct 2021.

Builds on

27 of 33 references.

References · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,217
  4. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 787
  5. 2017Focal Loss for Dense Object Detectioncited by 752
  6. 2021ImageNet-21K Pretraining for the Massescited by 613
  7. 2018The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scalecited by 544
  8. 2020Asymmetric Loss For Multi-Label Classificationcited by 381
  9. 2019Multi-Label Image Recognition with Graph Convolutional Networkscited by 322
  10. 2018A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decaycited by 226
  11. 2018Learning from positive and unlabeled data: a surveycited by 219
  12. 2016CNN-RNN: A Unified Framework for Multi-label Image Classificationcited by 190
15 more
  1. 2021Query2Label: A Simple Transformer Way to Multi-Label Classificationcited by 128
  2. 2020General Multi-label Image Classification with Transformerscited by 127
  3. 2019Learning a Deep ConvNet for Multi-label Classification with Partial Labelscited by 124
  4. 2020Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasetscited by 122
  5. 2020TResNet: High Performance GPU-Dedicated Architecturecited by 119
  6. 2019Cross-Modality Attention with Semantic Graph Embedding for Multi-Label Classificationcited by 79
  7. 2015Seeing through the Human Reporting Bias: Visual Classifiers from Noisy Human-Centric Labelscited by 64
  8. 2013Large-scale Multi-label Learning with Missing Labelscited by 58
  9. 2020Learning from Positive and Unlabeled Data with Arbitrary Positive Shiftcited by 23
  10. 2021MlTr: Multi-label Classification with Transformercited by 21
  11. 2021Multi-Label Image Classification with Contrastive Learningcited by 18
  12. 2016Improving Multi-label Learning with Missing Labels by Structured Semantic Correlationscited by 14
  13. 2018Multi-label Learning with Missing Labels using Mixed Dependency Graphscited by 14
  14. 2021Rethinking Crowdsourcing Annotation: Partial Annotation with Salient Labels for Multi-Label Image Classificationcited by 7
  15. 2020Improving Positive Unlabeled Learning: Practical AUL Estimation and New Training Method for Extremely Imbalanced Data Setscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 2; 2022: 3; 2023: 7; 2024: 9; 2025: 3; 2026: 1.

25 papers.

Sort:

By area:

  1. 2021ML-Decoder: Scalable and Versatile Classification Headcited by 79
  2. 2022Gradient Obfuscation Gives a False Sense of Security in Federated Learningcited by 39
  3. 2023Exploring Structured Semantic Prior for Multi Label Recognition with Incomplete Labelscited by 24
  4. 2022PIDray: A Large-scale X-ray Benchmark for Real-World Prohibited Item Detectioncited by 17
  5. 2023Learning in Imperfect Environment: Multi-Label Classification with Long-Tailed Distribution and Partial Labelscited by 17
  6. 2023Class-Distribution-Aware Pseudo Labeling for Semi-Supervised Multi-Label Learningcited by 16
  7. 2023Bridging the Gap between Model Explanations in Partially Annotated Multi-label Classificationcited by 11
  8. 2024CLIP-Decoder : ZeroShot Multilabel Classification using Multimodal CLIP Aligned Representationcited by 9
  9. 2023End-to-End Supervised Multilabel Contrastive Learningcited by 8
  10. 2023Positive Label Is All You Need for Multi-Label Classificationcited by 7
  11. 2025When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identificationcited by 5
  12. 2025Correlative and Discriminative Label Grouping for Multi-Label Visual Prompt Tuningcited by 4
13 more
  1. 2021The Klarna Product Page Dataset: Web Element Nomination with Graph Neural Networks and Large Language Modelscited by 2
  2. 2024Combining Supervised Learning and Reinforcement Learning for Multi-Label Classification Tasks with Partial Labelscited by 2
  3. 2024Dual-Decoupling Learning and Metric-Adaptive Thresholding for Semi-Supervised Multi-Label Learningcited by 2
  4. 2024Category-wise Fine-Tuning: Resisting Incorrect Pseudo-Labels in Multi-Label Image Classification with Partial Labelscited by 1
  5. 2024Top-K Pairwise Ranking: Bridging the Gap Among Ranking-Based Measures for Multi-Label Classificationcited by 1
  6. 2022Speech MOS multi-task learning and rater bias correctioncited by 0
  7. 2023Vision-language Assisted Attribute Learningcited by 0
  8. 2024Enhancing Small Object Encoding in Deep Neural Networks: Introducing Fast&Focused-Net with Volume-wise Dot Product Layercited by 0
  9. 2024Determined Multi-Label Learning via Similarity-Based Promptcited by 0
  10. 2024Free Performance Gain from Mixing Multiple Partially Labeled Samples in Multi-label Image Classificationcited by 0
  11. 2024A Survey on Incomplete Multi-label Learning: Recent Advances and Future Trendscited by 0
  12. 2025Incomplete Multi-Label Image Recognition by Co-learning Semantic-Aware Features and Label Recoverycited by 0
  13. 2026Adapting Dense Vision-Language Relationships for Multi-label Classification with Partial Labelcited by 0