Pith. sign in

REVIEW 2 cited by

HGCLIP: Exploring Vision-Language Models with Graph Representations for Hierarchical Understanding

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2311.14064 v3 pith:3T7EVTNU submitted 2023-11-23 cs.CV

classification cs.CV
keywords featuresgraphhierarchicalcategoriesclasshgcliphierarchyimage
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Object categories are typically organized into a multi-granularity taxonomic hierarchy. When classifying categories at different hierarchy levels, traditional uni-modal approaches focus primarily on image features, revealing limitations in complex scenarios. Recent studies integrating Vision-Language Models (VLMs) with class hierarchies have shown promise, yet they fall short of fully exploiting the hierarchical relationships. These efforts are constrained by their inability to perform effectively across varied granularity of categories. To tackle this issue, we propose a novel framework (HGCLIP) that effectively combines CLIP with a deeper exploitation of the Hierarchical class structure via Graph representation learning. We explore constructing the class hierarchy into a graph, with its nodes representing the textual or image features of each category. After passing through a graph encoder, the textual features incorporate hierarchical structure information, while the image features emphasize class-aware features derived from prototypes through the attention mechanism. Our approach demonstrates significant improvements on 11 diverse visual recognition benchmarks. Our codes are fully available at https://github.com/richard-peng-xia/HGCLIP.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Learning Taxonomic Trees with Hierarchical Representation Regularization for Large Multimodal Models

    cs.CV 2026-07 conditional novelty 6.0 of 10

    HiR² extracts coarse-to-fine visual features from LMM layers and regularizes them with Lorentz entailment cones and unit-sphere dispersive loss, improving hierarchical consistency across models and fine-tuning methods.

  2. Analyzing Hierarchical Structure in Vision Models with Sparse Autoencoders

    cs.CV 2025-05 conditional novelty 4.0 of 10

    SAE features in later DINOv2 layers align with ImageNet hierarchy, with two new metrics proposed to measure such alignment.

Pith tools