Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tissera, Dumindu, Awadallah, Omar, Danish, Muhammad Umair, Sadhu, Ayan, Grolinger, Katarina
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908395964989440
author Tissera, Dumindu
Awadallah, Omar
Danish, Muhammad Umair
Sadhu, Ayan
Grolinger, Katarina
author_facet Tissera, Dumindu
Awadallah, Omar
Danish, Muhammad Umair
Sadhu, Ayan
Grolinger, Katarina
contents Multi-label Classification (MLC) assigns an instance to one or more non-exclusive classes. A challenge arises when the dataset contains a large proportion of instances with no assigned class, referred to as negative data, which can overwhelm the learning process and hinder the accurate identification and classification of positive instances. Nevertheless, it is common in MLC applications such as industrial defect detection, agricultural disease identification, and healthcare diagnosis to encounter large amounts of negative data. Assigning a separate negative class to these instances further complicates the learning objective and introduces unnecessary redundancies. To address this challenge, we redesign standard MLC loss functions by deriving a likelihood of any class being present, formulated by a normalized weighted geometric mean of the predicted class probabilities. We introduce a regularization parameter that controls the relative contribution of the absent class probabilities to the any-class presence likelihood in positive instances. The any-class presence likelihood complements the multi-label learning by encouraging the network to become more aware of implicit positive instances and improve the label classification within those positive instances. Experiments on large-scale datasets with negative data: SewerML, modified COCO, and ChestX-ray14, across various networks and base loss functions show that our loss functions consistently improve MLC performance of their standard loss counterparts, achieving gains of up to 6.01 percentage points in F1, 8.06 in F2, and 3.11 in mean average precision, all without additional parameters or computational complexity. Code available at: https://github.com/ML-for-Sensor-Data-Western/gmean-mlc
format Preprint
id arxiv_https___arxiv_org_abs_2506_05721
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data
Tissera, Dumindu
Awadallah, Omar
Danish, Muhammad Umair
Sadhu, Ayan
Grolinger, Katarina
Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
68T05 (Primary) 62H30 (Secondary)
I.2.6; I.5.4
Multi-label Classification (MLC) assigns an instance to one or more non-exclusive classes. A challenge arises when the dataset contains a large proportion of instances with no assigned class, referred to as negative data, which can overwhelm the learning process and hinder the accurate identification and classification of positive instances. Nevertheless, it is common in MLC applications such as industrial defect detection, agricultural disease identification, and healthcare diagnosis to encounter large amounts of negative data. Assigning a separate negative class to these instances further complicates the learning objective and introduces unnecessary redundancies. To address this challenge, we redesign standard MLC loss functions by deriving a likelihood of any class being present, formulated by a normalized weighted geometric mean of the predicted class probabilities. We introduce a regularization parameter that controls the relative contribution of the absent class probabilities to the any-class presence likelihood in positive instances. The any-class presence likelihood complements the multi-label learning by encouraging the network to become more aware of implicit positive instances and improve the label classification within those positive instances. Experiments on large-scale datasets with negative data: SewerML, modified COCO, and ChestX-ray14, across various networks and base loss functions show that our loss functions consistently improve MLC performance of their standard loss counterparts, achieving gains of up to 6.01 percentage points in F1, 8.06 in F2, and 3.11 in mean average precision, all without additional parameters or computational complexity. Code available at: https://github.com/ML-for-Sensor-Data-Western/gmean-mlc
title Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data
topic Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
68T05 (Primary) 62H30 (Secondary)
I.2.6; I.5.4
url https://arxiv.org/abs/2506.05721