Addressing Granularity-induced Semantic Drift in OvOD via Graph-guided semantically consistent representation

摘要

Open-vocabulary object detection (OvOD) uses Vision-Language Models (VLMs) to detect arbitrary categories specified by natural language. However, existing methods often struggle with performance instability caused by granularity-induced semantic drift, which arises from misaligned label embeddings across varying levels of specificity. In this paper, we propose GraSecon, a Graph-guided Semantically Consistent representation framework that enhances zero-shot detection robustness without requiring additional training. We construct a hierarchical Fine-grained Semantic Graph enriched with visually grounded attributes from large language models (LLMs). This graph captures hierarchical, sibling and cross-level relations, enabling controlled Laplacian refinement to harmonize the embedding space and improve visual-semantic alignment. To strengthen fine-grained discriminability, we introduce a Key Semantic Node Mining module that identifies and anchors semantically sensitive nodes, ensuring robust feature representation. Furthermore, our Semantic Relevance-Driven Laplacian Propagation adaptively propagates information, promoting coherent and context-aware embedding alignment across granularities. Extensive experiments on the iNatLoc and FSOD datasets demonstrate that GraSecon outperforms prior SOTA methods, achieving average mAP50 improvements of 6.5% and 5.4%. Code is publicly available at: https://github.com/minoslab-csu/GraSecon.