Multi-Instance Partial-Label Learning with Margin Adjustment

2025-01-22 · Wei Tang, Yin-Fang Yang, Zhaofei Wang, Weijia Zhang, Min-Ling Zhang

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.

📄 PDF Abstract BibTeX arXiv:2501.12597

Code (1)

tangw-seu/miplma 공식 구현 pytorch

Tasks

Partial Label Learning

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Attention 설명 없음

Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning

2025-12-19 · Wei Tang, Yin-Fang Yang, Weijia Zhang, Min-Ling Zhang arxiv

Multi-instance partial-label learning (MIPL) is a weakly supervised framework that extends the principles of multi-instance learning (MIL) and partial-label learning (PLL) to address the challenges of inexact supervision…

Online Multiclass Classification Based on Prediction Margin for Partial Feedback

2019-02-04 · Takuo Kaneko, Issei Sato, Masashi Sugiyama

We consider the problem of online multiclass classification with partial feedback, where an algorithm predicts a class for a new instance in each round and only receives its correctness. Although several methods have bee…

Classification General Classification

On Characterizing and Mitigating Imbalances in Multi-Instance Partial Label Learning

2024-07-13 · Kaifu Wang, Efthymia Tsamoura, Dan Roth

*Multi-Instance Partial Label Learning* (MI-PLL) is a weakly-supervised learning setting encompassing *partial label learning*, *latent structural learning*, and *neurosymbolic learning*. Unlike supervised learning, in M…

Long-tail Learning Partial Label Learning Weakly-supervised Learning

Multi-Instance Partial-Label Learning: Towards Exploiting Dual Inexact Supervision

2022-12-18 · Wei Tang, Weijia Zhang, Min-Ling Zhang

Weakly supervised machine learning algorithms are able to learn from ambiguous samples or labels, e.g., multi-instance learning or partial-label learning. However, in some real-world tasks, each training sample is associ…

Gaussian Processes Partial Label Learning

Semantic-Aware Graph Matching Mechanism for Multi-Label Image Recognition

2023-04-21 · Yanan Wu, Songhe Feng, Yang Wang

Multi-label image recognition aims to predict a set of labels that present in an image. The key to deal with such problem is to mine the associations between image contents and labels, and further obtain the correct assi…

Few-Shot Learning Graph Matching Multi-Label Image Recognition