mlsanityData to 14 Oct 2026

Disambiguated Attention Embedding for Multi-Instance Partial-Label Learning

arXiv 2305.16912 ↗First posted 26 May 2023cs.LGcited by 10

Not on the map. Why?

Abstract (arXiv)

In many real-world tasks, the concerned objects can be represented as a multi-instance bag associated with a candidate label set, which consists of one ground-truth label and several false positive labels. Multi-instance partial-label learning (MIPL) is a learning paradigm to deal with such tasks and has achieved favorable performances. Existing MIPL approach follows the instance-space paradigm by assigning augmented candidate label sets of bags to each instance and aggregating bag-level labels from instance-level labels. However, this scheme may be suboptimal as global bag-level information is ignored and the predicted labels of bags are sensitive to predictions of negative instances. In this paper, we study an alternative scheme where a multi-instance bag is embedded into a single vector representation. Accordingly, an intuitive algorithm named DEMIPL, i.e., Disambiguated attention Embedding for Multi-Instance Partial-Label learning, is proposed. DEMIPL employs a disambiguation attention mechanism to aggregate a multi-instance bag into a single vector representation, followed by a momentum-based disambiguation strategy to identify the ground-truth label from the candidate label set. Furthermore, we introduce a real-world MIPL dataset for colorectal cancer classification. Experimental results on benchmark and real-world datasets validate the superiority of DEMIPL against the compared MIPL and partial-label learning approaches.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 28 of its 60 references that are in the map. First posted on arXiv 26 May 2023.

Builds on

28 of 60 references.

References · 28

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  4. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,391
  5. 2018Attention-based Deep Multiple Instance Learningcited by 1,095
  6. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,059
  7. 2020Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Imagescited by 745
  8. 2021TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classificationcited by 555
  9. 2020Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learningcited by 478
  10. 2022DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classificationcited by 256
  11. 2021Attention Mechanisms in Computer Vision: A Surveycited by 232
  12. 2016Multiple Instance Learning: A Survey of Problem Characteristics and Applicationscited by 164
16 more
  1. 2016Revisiting Multiple Instance Neural Networkscited by 119
  2. 2019Exact Gaussian Processes on a Million Data Pointscited by 119
  3. 2020Progressive Identification of True Labels for Partial-Label Learningcited by 102
  4. 2020Provably Consistent Partial-Label Learningcited by 92
  5. 2017Learning from Complementary Labelscited by 88
  6. 2021Leveraged Weighted Loss for Partial Label Learningcited by 66
  7. 2022Additive MIL: Intrinsically Interpretable Multiple Instance Learning for Pathologycited by 58
  8. 2021Instance-Dependent Partial Label Learningcited by 49
  9. 2022SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learningcited by 31
  10. 2019GM-PLL: Graph Matching based Partial Label Learningcited by 23
  11. 2019A Regularization Approach for Instance-Based Superset Label Learningcited by 21
  12. 2022Multi-Instance Causal Representation Learning for Instance Label Prediction and Out-of-Distribution Generalizationcited by 17
  13. 2021Learning from Ambiguous Labels for Lung Nodule Malignancy Predictioncited by 15
  14. 2022Multi-Instance Partial-Label Learning: Towards Exploiting Dual Inexact Supervisioncited by 9
  15. 2021Pedestrian Attribute Recognition in Video Surveillance Scenarios Based on View-attribute Attention Localizationcited by 8
  16. 2021Non-I.I.D. Multi-Instance Learning for Predicting Instance and Bag Labels using Variational Auto-Encodercited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 6; 2026: 3.

10 papers.

  1. 2025Realistic Evaluation of Deep Partial-Label Learning Algorithmscited by 12
  2. 2026ASMIL: Attention-Stabilized Multiple Instance Learning for Whole Slide Imagingcited by 6
  3. 2025Multi-Instance Partial-Label Learning with Margin Adjustmentcited by 5
  4. 2024Exploiting Conjugate Label Information for Multi-Instance Partial-Label Learningcited by 3
  5. 2025Tuning the Right Foundation Models is What you Need for Partial Label Learningcited by 2
  6. 2025Unleashing the Power of Vision-Language Models for Long-Tailed Multi-Label Visual Recognitioncited by 1
  7. 2025Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learningcited by 1
  8. 2025Neuro-symbolic Weak Supervision: Theory and Semanticscited by 0
  9. 2026Recent advances in weakly supervised learning: New supervision paradigms, assumption relaxations, and practical solutionscited by 0
  10. 2026Joint Class-Time Learning for Video Classification with Multi-Instance Partial-Label Learningcited by 0