analiza aiqbench
InterHier addresses a specific bottleneck in open-vocabulary object detection by replacing rigid, hand-crafted semantic connectors with learnable contexts that better capture hierarchical relationships. This approach aligns visual region embeddings with textual prompts more effectively than existing fixed-connector methods, offering a practical upgrade for current computer vision models without requiring architectural overhauls.
InterHier: Learning Interconnected Hierarchical Semantics for Open-Vocabulary Object Detection
arXiv:2609.24026v1 Announce Type: cross Abstract: In this paper, we investigate the limitations of fixed, hand-crafted connectors in hierarchical semantic representations for open-vocabulary object detection. Existing methods establish semantic relationships between base categories and unseen novel categories by placing a fixed connector between adjacent super-/sub-categories. However, such fixed connectors may not optimally capture the relationships within a semantic hierarchy. To address this limitation, we propose interconnected hierarchical semantic representations (InterHier), which utilize a prepended learnable context to globally guide the interpretation of prompts containing hierarchical relationships. InterHier operates in two main stages. First, it constructs a hierarchy-aware prompt by integrating super-/sub-categories and prepending a learnable context. Second, it optimizes this learnable context to align visual region embeddings and textual embeddings. InterHier consistently improves performance over methods that rely on fixed connectors and can be seamlessly integrated into existing open-vocabulary object detection models. Experiments on open-vocabulary object detection benchmarks demonstrate that InterHier achieves competitive performance against state-of-the-art methods.
Abstract:In this paper, we investigate the limitations of fixed, hand-crafted connectors in hierarchical semantic representations for open-vocabulary object detection. Existing methods establish semantic relationships between base categories and unseen novel categories by placing a fixed connector between adjacent super-/sub-categories. However, such fixed connectors may not optimally capture the relationships within a semantic hierarchy. To address this limitation, we propose interconnected hierarchical semantic representations (InterHier), which utilize a prepended learnable context to globally guide the interpretation of prompts containing hierarchical relationships. InterHier operates in two main stages. First, it constructs a hierarchy-aware prompt by integrating super-/sub-categories and prepending a learnable context. Second, it optimizes this learnable context to align visual region embeddings and textual embeddings. InterHier consistently improves performance over methods that rely on fixed connectors and can be seamlessly integrated into existing open-vocabulary object detection models. Experiments on open-vocabulary object detection benchmarks demonstrate that InterHier achieves competitive performance against state-of-the-art methods.
12 pages, 6 figures. Published in IEEE Access
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
arXiv:2609.24026 [cs.CV]
(or arXiv:2609.24026v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2609.24026 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
IEEE Access, vol. 14, pp. 14709-14721, 2026
https://doi.org/10.1109/ACCESS.2026.3655392 Focus to learn more DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 276 cuvinte
Subiecte conexe
LangMap: A Human-Verified Benchmark for Hierarchical Open-Vocabulary Goal Navigation
arXiv · 2 oct. 2026
A Topological Representation with Object-Path Graphs for Open-Vocabulary Instance Navigation
arXiv · 22 sept. 2026
LASA: A Weak Supervision Method for Open-Vocabulary Scene Sketch Semantic Segmentation
arXiv · 11 iun. 2026
T-FunS3D: Task-Driven Hierarchical Open-Vocabulary 3D Functionality Segmentation
arXiv · 5 iun. 2026