mlsanityData to 14 Oct 2026

Multi-Instance Partial-Label Learning with Margin Adjustment

arXiv 2501.12597 ↗First posted 22 Jan 2025cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Multi-instance partial-label learning (MIPL) is an emerging learning framework where each training sample is represented as a multi-instance bag associated with a candidate label set. Existing MIPL algorithms often overlook the margins for attention scores and predicted probabilities, leading to suboptimal generalization performance. A critical issue with these algorithms is that the highest prediction probability of the classifier may appear on a non-candidate label. In this paper, we propose an algorithm named MIPLMA, i.e., Multi-Instance Partial-Label learning with Margin Adjustment, which adjusts the margins for attention scores and predicted probabilities. We introduce a margin-aware attention mechanism to dynamically adjust the margins for attention scores and propose a margin distribution loss to constrain the margins between the predicted probabilities on candidate and non-candidate label sets. Experimental results demonstrate the superior performance of MIPLMA over existing MIPL algorithms, as well as other well-established multi-instance learning algorithms and partial-label learning algorithms.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 24 of its 53 references that are in the map. First posted on arXiv 22 Jan 2025.

Builds on

24 of 53 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  4. 2017Deep Setscited by 1,421
  5. 2018Attention-based Deep Multiple Instance Learningcited by 1,095
  6. 2021TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classificationcited by 555
  7. 2022DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classificationcited by 256
  8. 2016Multiple Instance Learning: A Survey of Problem Characteristics and Applicationscited by 164
  9. 2016Revisiting Multiple Instance Neural Networkscited by 119
  10. 2018Predicting the Generalization Gap in Deep Networks with Margin Distributionscited by 113
  11. 2020Progressive Identification of True Labels for Partial-Label Learningcited by 102
  12. 2020Provably Consistent Partial-Label Learningcited by 92
12 more
  1. 2021Multiple instance active learning for object detectioncited by 77
  2. 2021Leveraged Weighted Loss for Partial Label Learningcited by 66
  3. 2023Unbiased Multiple Instance Learning for Weakly Supervised Video Anomaly Detectioncited by 64
  4. 2022Progressive Purification for Instance-Dependent Partial Label Learningcited by 23
  5. 2022Multi-Instance Causal Representation Learning for Instance Label Prediction and Out-of-Distribution Generalizationcited by 17
  6. 2021Learning from Ambiguous Labels for Lung Nodule Malignancy Predictioncited by 15
  7. 2023On Learning Latent Models with Multi-Instance Weak Supervisioncited by 13
  8. 2023Disambiguated Attention Embedding for Multi-Instance Partial-Label Learningcited by 10
  9. 2022Learning with Partial Labels from Semi-supervised Perspectivecited by 9
  10. 2022Multi-Instance Partial-Label Learning: Towards Exploiting Dual Inexact Supervisioncited by 9
  11. 2023Data-driven Knowledge Fusion for Deep Multi-instance Learningcited by 3
  12. 2024Exploiting Conjugate Label Information for Multi-Instance Partial-Label Learningcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 1.

5 papers.

  1. 2025Tuning the Right Foundation Models is What you Need for Partial Label Learningcited by 2
  2. 2025Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learningcited by 1
  3. 2025Neuro-symbolic Weak Supervision: Theory and Semanticscited by 0
  4. 2025Cluster-Level Sparse Multi-Instance Learning for Whole-Slide Imagescited by 0
  5. 2026Joint Class-Time Learning for Video Classification with Multi-Instance Partial-Label Learningcited by 0