AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

OPMapper: Enhancing Open-Vocabulary Semantic Segmentation with Multi-Guidance Information

Xuehui Wang, Chongjie Si, Xue Yang, Yuzhi Zhao, Wenhai Wang, Xiaokang Yang, Wei Shen

NeurIPS 2025 · Vision-language and multimodal › CLIP and zero-shot · approach: Open-vocabulary alignment from VLMs · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes OPMapper, an open-vocabulary semantic segmentation method that enhances CLIP-based dense prediction with multi-guidance information (per the title; abstract truncated).

Problem

Open-vocabulary semantic segmentation requires per-pixel labels from open-ended text vocabularies, but CLIP's image-level pretraining hinders dense prediction; existing fixes either fine-tune CLIP at high cost or use training-free attention refinements that favor local smoothness over global semanti

Approach

Enhances CLIP-based dense prediction with multi-guidance information rather than full fine-tuning or purely local attention refinement; the abstract is truncated so the specific mechanism is not stated.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy