Feature Identification for Hierarchical Contrastive Learning

• URL: http://arxiv.org/abs/2510.00837v1
• Date: Wed, 01 Oct 2025 12:46:47 GMT
• Title: Feature Identification for Hierarchical Contrastive Learning
• Authors: Julius Ott, Nastassia Vysotskaya, Huawei Sun, Lorenzo Servadei, Robert Wille,
• Abstract summary: We propose two novel hierarchical contrastive learning (HMLC) methods.<n>Our approach explicitly models inter-class relationships and imbalanced class distribution at higher hierarchy levels.<n>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.
• Score: 7.655211354400059
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Learning Consistent Taxonomic Classification through Hierarchical Reasoning [61.372270953201955]
  We propose a two-stage, hierarchy-based reasoning framework designed to improve leaf-level accuracy and hierarchical consistency in taxonomic classification.<n>Our framework, implemented on the Qwen2.5-VL-7B model, outperforms its original 72B counterpart by over 10% in both leaf-level and hierarchical consistency accuracy.
  arXiv  Detail & Related papers  (2026-01-21T03:00:00Z)
• Balanced Hierarchical Contrastive Learning with Decoupled Queries for Fine-grained Object Detection in Remote Sensing Images [14.170021143579435]
  We propose a balanced hierarchical contrastive loss combined with a decoupled learning strategy within the detection transformer (DETR) framework.<n>The proposed loss introduces learnable class prototypes and equilibrates gradients contributed by different classes at each hierarchical level.<n> Experiments on three fine-grained datasets with hierarchical annotations demonstrate that our method outperforms state-of-the-art approaches.
  arXiv  Detail & Related papers  (2025-12-30T08:35:54Z)
• A class-driven hierarchical ResNet for classification of multispectral remote sensing images [12.282079123411947]
  We present a class-driven hierarchical Residual Neural Network (ResNet) for modelling the classification of Time Series (TS) of multispectral images at different semantical class levels.<n>We leverage on hierarchy-penalty maps to discourage incoherent hierarchical transitions within the classification.<n>The experimental results, obtained on two tiles of the Amazonian Forest on 12 monthly composites of Sentinel 2 images, demonstrate the effectiveness of the hierarchical approach.
  arXiv  Detail & Related papers  (2025-10-09T10:47:52Z)
• A Semantics-Aware Hierarchical Self-Supervised Approach to Classification of Remote Sensing Images [12.282079123411947]
  We present a novel Semantics-Aware Hierarchical Consensus (SAHC) method for learning hierarchical features and relationships.<n>The SAHC method is evaluated on three benchmark datasets with different degrees of hierarchical complexity.<n> Experimental results show both the effectiveness of the proposed approach in guiding network learning and the robustness of the hierarchical consensus for remote sensing image classification tasks.
  arXiv  Detail & Related papers  (2025-10-06T15:30:39Z)
• Deep Taxonomic Networks for Unsupervised Hierarchical Prototype Discovery [5.300910554558862]
  Existing methods often tie the structure to the number of classes and underutilize the rich prototype information available at intermediate hierarchical levels.<n>We introduce deep taxonomic networks, a novel deep latent variable approach designed to bridge these gaps.
  arXiv  Detail & Related papers  (2025-09-28T03:13:32Z)
• Cross-Hierarchical Bidirectional Consistency Learning for Fine-Grained Visual Classification [1.757077789361314]
  We propose a novel Cross-Hierarchical Bidirectional Consistency Learning (CHBC) framework to improve classification accuracy and consistency.<n>The CHBC framework extracts discriminative features across various hierarchies using a specially designed module to decompose and enhance attention masks.<n> Experiments on three widely used FGVC datasets validate the effectiveness of the CHBC framework.
  arXiv  Detail & Related papers  (2025-04-18T10:30:17Z)
• Generating Hierarchical Structures for Improved Time Series Classification Using Stochastic Splitting Functions [0.0]
  This study introduces a novel hierarchical divisive clustering approach with splitting functions (SSFs) to enhance classification performance in multi-class datasets through hierarchical classification (HC) The method has the unique capability of generating hierarchy without requiring explicit information, making it suitable for datasets lacking prior knowledge of hierarchy.
  arXiv  Detail & Related papers  (2023-09-21T10:34:50Z)
• Weakly-supervised Action Localization via Hierarchical Mining [76.00021423700497]
  Weakly-supervised action localization aims to localize and classify action instances in the given videos temporally with only video-level categorical labels. We propose a hierarchical mining strategy under video-level and snippet-level manners, i.e., hierarchical supervision and hierarchical consistency mining. We show that HiM-Net outperforms existing methods on THUMOS14 and ActivityNet1.3 datasets with large margins by hierarchically mining the supervision and consistency.
  arXiv  Detail & Related papers  (2022-06-22T12:19:09Z)
• Ranking hierarchical multi-label classification results with mLPRs [4.869182515096001]
  We focus on the less attended second-stage question while adhering to the given class hierarchy.<n>We introduce a new objective function, called CATCH, to ensure reasonable classification performance.<n>Our approach was evaluated on a synthetic dataset and two real datasets.
  arXiv  Detail & Related papers  (2022-05-16T17:43:35Z)
• The Overlooked Classifier in Human-Object Interaction Recognition [82.20671129356037]
  We encode the semantic correlation among classes into the classification head by initializing the weights with language embeddings of HOIs. We propose a new loss named LSE-Sign to enhance multi-label learning on a long-tailed dataset. Our simple yet effective method enables detection-free HOI classification, outperforming the state-of-the-arts that require object detection and human pose by a clear margin.
  arXiv  Detail & Related papers  (2022-03-10T23:35:00Z)
• Self-Supervised Class Incremental Learning [51.62542103481908]
  Existing Class Incremental Learning (CIL) methods are based on a supervised classification framework sensitive to data labels. When updating them based on the new class data, they suffer from catastrophic forgetting: the model cannot discern old class data clearly from the new. In this paper, we explore the performance of Self-Supervised representation learning in Class Incremental Learning (SSCIL) for the first time.
  arXiv  Detail & Related papers  (2021-11-18T06:58:19Z)
• Hierarchical Modeling for Out-of-Scope Domain and Intent Classification [55.23920796595698]
  This paper focuses on out-of-scope intent classification in dialog systems. We propose a hierarchical multi-task learning approach based on a joint model to classify domain and intent simultaneously. Experiments show that the model outperforms existing methods in terms of accuracy, out-of-scope recall and F1.
  arXiv  Detail & Related papers  (2021-04-30T06:38:23Z)
• Inducing a hierarchy for multi-class classification problems [11.58041597483471]
  In applications where categorical labels follow a natural hierarchy, classification methods that exploit the label structure often outperform those that do not. In this paper, we investigate a class of methods that induce a hierarchy that can similarly improve classification performance over flat classifiers. We demonstrate the effectiveness of the class of methods both for discovering a latent hierarchy and for improving accuracy in principled simulation settings and three real data applications.
  arXiv  Detail & Related papers  (2021-02-20T05:40:42Z)
• Binary Classification from Multiple Unlabeled Datasets via Surrogate Set Classification [94.55805516167369]
  We propose a new approach for binary classification from m U-sets for $mge2$. Our key idea is to consider an auxiliary classification task called surrogate set classification (SSC)
  arXiv  Detail & Related papers  (2021-02-01T07:36:38Z)
• Coherent Hierarchical Multi-Label Classification Networks [56.41950277906307]
  C-HMCNN(h) is a novel approach for HMC problems, which exploits hierarchy information in order to produce predictions coherent with the constraint and improve performance. We conduct an extensive experimental analysis showing the superior performance of C-HMCNN(h) when compared to state-of-the-art models.
  arXiv  Detail & Related papers  (2020-10-20T09:37:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.