Explaining, Verifying, and Aligning Semantic Hierarchies in Vision-Language Model Embeddings

• URL: http://arxiv.org/abs/2603.26798v1
• Date: Thu, 26 Mar 2026 00:38:38 GMT
• Title: Explaining, Verifying, and Aligning Semantic Hierarchies in Vision-Language Model Embeddings
• Abstract summary: We present a post-hoc framework to explain, verify, and align semantic hierarchies induced by a VLM over a given set of child classes.<n>We quantify plausibility by comparing the extracted tree against human retrieval using efficient tree-aware and edge-level consistency measures, and we evaluate utility via explainable hierarchical tree-traversal inference.
• Score: 10.299190830046872
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision-language model (VLM) encoders such as CLIP enable strong retrieval and zero-shot classification in a shared image-text embedding space, yet the semantic organization of this space is rarely inspected. We present a post-hoc framework to explain, verify, and align the semantic hierarchies induced by a VLM over a given set of child classes. First, we extract a binary hierarchy by agglomerative clustering of class centroids and name internal nodes by dictionary-based matching to a concept bank. Second, we quantify plausibility by comparing the extracted tree against human ontologies using efficient tree- and edge-level consistency measures, and we evaluate utility via explainable hierarchical tree-traversal inference with uncertainty-aware early stopping (UAES). Third, we propose an ontology-guided post-hoc alignment method that learns a lightweight embedding-space transformation, using UMAP to generate target neighborhoods from a desired hierarchy. Across 13 pretrained VLMs and 4 image datasets, our method finds systematic modality differences: image encoders are more discriminative, while text encoders induce hierarchies that better match human taxonomies. Overall, the results reveal a persistent trade-off between zero-shot accuracy and ontological plausibility and suggest practical routes to improve semantic alignment in shared embedding spaces.

Related papers

• Online Continual Learning with Dynamic Label Hierarchies [72.33335166136045]
  We introduce a new problem setting, DHOCL, where severity evolve across granularities and each sample provides supervision at a single hierarchical level.<n>In this setting, we find two fundamental issues: (i) partial supervision under mixed granularities provides only point-wise signals over an evolving path-wise hierarchy, which constrains plasticity and undermines cross-level semantic consistency.<n>We propose HALO, which adaptively combines complementary classification heads, regularized by organized learnable hierarchical prototypes, enabling rapid adaptation, hierarchical consistency, and structured knowledge consolidation as the taxonomy evolves.
  arXiv  Detail & Related papers  (2026-05-12T08:20:23Z)
• TreeGaussian: Tree-Guided Cascaded Contrastive Learning for Hierarchical Consistent 3D Gaussian Scene Segmentation and Understanding [19.718058183540624]
  We introduce TreeGaussian, a tree-guided cascaded contrastive learning framework.<n>By constructing a multi-level object tree, TreeGaussian enables structured learning across object-part hierarchies.<n>A graph-based denoising module is introduced to align views while suppressing unstable Gaussian points.
  arXiv  Detail & Related papers  (2026-03-31T10:22:28Z)
• Improving LLM Reasoning with Homophily-aware Structural and Semantic Text-Attributed Graph Compression [55.51959317490934]
  Large language models (LLMs) have demonstrated promising capabilities in Text-Attributed Graph (TAG) understanding.<n>We argue that graphs inherently contain rich structural and semantic information, and that their effective exploitation can unlock potential gains in LLMs reasoning performance.<n>We propose Homophily-aware Structural and Semantic Compression for LLMs (HS2C), a framework centered on exploiting graph homophily.
  arXiv  Detail & Related papers  (2026-01-13T03:35:18Z)
• Hierarchy-Aware Fine-Tuning of Vision-Language Models [18.244518940229202]
  Vision-Language Models learn powerful multimodal representations through large-scale image-text pretraining.<n>Standard approaches treat labels as flat categories and require full fine-tuning, which is expensive and produces inconsistent predictions.<n>We propose an efficient hierarchy-aware fine-tuning framework that updates a few parameters while enforcing structural consistency.
  arXiv  Detail & Related papers  (2025-12-25T06:44:33Z)
• Hierarchical Representation Matching for CLIP-based Class-Incremental Learning [80.2317078787969]
  Class-Incremental Learning (CIL) aims to endow models with the ability to continuously adapt to evolving data streams.<n>Recent advances in pre-trained vision-language models (e.g., CLIP) provide a powerful foundation for this task.<n>We introduce HiErarchical Representation MAtchiNg (HERMAN) for CLIP-based CIL.
  arXiv  Detail & Related papers  (2025-09-26T17:59:51Z)
• A Hierarchical Semantic Distillation Framework for Open-Vocabulary Object Detection [47.18069715855738]
  We propose a hierarchical semantic distillation framework named HD-OVD to construct a comprehensive distillation process.<n>Our HD-OVD inherits generalizable recognition ability from CLIP in instance, class, and image levels.<n>We boost the novel AP on the OV-COCO dataset to 46.4% with a ResNet50 backbone, which outperforms others by a clear margin.
  arXiv  Detail & Related papers  (2025-03-13T08:27:18Z)
• Learning and Evaluating Hierarchical Feature Representations [3.770103075126785]
  We propose a novel framework, Hierarchical Composition of Orthogonal Subspaces (Hier-COS)<n>Hier-COS learns to map deep feature embeddings into a vector space that is, by design, consistent with the structure of a given taxonomy tree.<n>We demonstrate that Hier-COS achieves state-of-the-art hierarchical performance across all the datasets while simultaneously beating top-1 accuracy in all but one case.
  arXiv  Detail & Related papers  (2025-03-10T20:59:41Z)
• SGC-Net: Stratified Granular Comparison Network for Open-Vocabulary HOI Detection [16.89965584177711]
  Recent open-vocabulary human-object interaction (OV-HOI) detection methods rely on large language model (LLM) for generating auxiliary descriptions and leverage knowledge distilled from CLIP to detect unseen interaction categories.<n>Despite their effectiveness, these methods face two challenges: (1) feature granularity deficiency, due to reliance on last layer visual features for text alignment, leading to the neglect of crucial object-level details from intermediate layers; (2) semantic similarity confusion, resulting from CLIP's inherent biases toward certain classes, while LLM-generated descriptions based solely on labels fail to adequately capture inter-class similarities.
  arXiv  Detail & Related papers  (2025-03-01T09:26:05Z)
• Bidirectional Logits Tree: Pursuing Granularity Reconcilement in Fine-Grained Classification [89.20477310885731]
  This paper addresses the challenge of Granularity Competition in fine-grained classification tasks.<n>Existing approaches typically develop independent hierarchy-aware models based on shared features extracted from a common base encoder.<n>We propose a novel framework called the Bidirectional Logits Tree (BiLT) for Granularity Reconcilement.
  arXiv  Detail & Related papers  (2024-12-17T10:42:19Z)
• Integrating Hierarchical Semantic into Iterative Generation Model for Entailment Tree Explanation [7.5496857647335585]
  We propose an architecture of integrating the Hierarchical Semantics of sentences under the framework of Controller-Generator (HiSCG) to explain answers. The proposed method achieves comparable performance on all three settings of the EntailmentBank dataset.
  arXiv  Detail & Related papers  (2024-09-26T11:46:58Z)
• Towards Realistic Zero-Shot Classification via Self Structural Semantic Alignment [53.2701026843921]
  Large-scale pre-trained Vision Language Models (VLMs) have proven effective for zero-shot classification. In this paper, we aim at a more challenging setting, Realistic Zero-Shot Classification, which assumes no annotation but instead a broad vocabulary. We propose the Self Structural Semantic Alignment (S3A) framework, which extracts structural semantic information from unlabeled data while simultaneously self-learning.
  arXiv  Detail & Related papers  (2023-08-24T17:56:46Z)
• 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)

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.