Saved in:
Bibliographic Details
Main Authors: Ott, Julius, Vysotskaya, Nastassia, Sun, Huawei, Servadei, Lorenzo, Wille, Robert
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.00837
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915528428224512
author Ott, Julius
Vysotskaya, Nastassia
Sun, Huawei
Servadei, Lorenzo
Wille, Robert
author_facet Ott, Julius
Vysotskaya, Nastassia
Sun, Huawei
Servadei, Lorenzo
Wille, Robert
contents Hierarchical classification is a crucial task in many applications, where objects are organized into multiple levels of categories. However, conventional classification approaches often neglect inherent inter-class relationships at different hierarchy levels, thus missing important supervisory signals. Thus, we propose two novel hierarchical contrastive learning (HMLC) methods. The first, leverages a Gaussian Mixture Model (G-HMLC) and the second uses an attention mechanism to capture hierarchy-specific features (A-HMLC), imitating human processing. Our approach explicitly models inter-class relationships and imbalanced class distribution at higher hierarchy levels, enabling fine-grained clustering across all hierarchy levels. On the competitive CIFAR100 and ModelNet40 datasets, our method achieves state-of-the-art performance in linear evaluation, outperforming existing hierarchical contrastive learning methods by 2 percentage points in terms of accuracy. The effectiveness of our approach is backed by both quantitative and qualitative results, highlighting its potential for applications in computer vision and beyond.
format Preprint
id arxiv_https___arxiv_org_abs_2510_00837
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Feature Identification for Hierarchical Contrastive Learning
Ott, Julius
Vysotskaya, Nastassia
Sun, Huawei
Servadei, Lorenzo
Wille, Robert
Computer Vision and Pattern Recognition
Artificial Intelligence
Hierarchical classification is a crucial task in many applications, where objects are organized into multiple levels of categories. However, conventional classification approaches often neglect inherent inter-class relationships at different hierarchy levels, thus missing important supervisory signals. Thus, we propose two novel hierarchical contrastive learning (HMLC) methods. The first, leverages a Gaussian Mixture Model (G-HMLC) and the second uses an attention mechanism to capture hierarchy-specific features (A-HMLC), imitating human processing. Our approach explicitly models inter-class relationships and imbalanced class distribution at higher hierarchy levels, enabling fine-grained clustering across all hierarchy levels. On the competitive CIFAR100 and ModelNet40 datasets, our method achieves state-of-the-art performance in linear evaluation, outperforming existing hierarchical contrastive learning methods by 2 percentage points in terms of accuracy. The effectiveness of our approach is backed by both quantitative and qualitative results, highlighting its potential for applications in computer vision and beyond.
title Feature Identification for Hierarchical Contrastive Learning
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2510.00837