CP-CLIP: Customized Parameter Generation for Open-vocabulary Semantic Segmentation

Zelin Peng; Zhengqin Xu; Feilong Tang; Wei Shen

AAAI 2026technical0 citations

CP-CLIP: Customized Parameter Generation for Open-vocabulary Semantic Segmentation

Zelin Peng, Zhengqin Xu, Feilong Tang, Wei Shen

Abstract

Open-vocabulary semantic segmentation aims to assign pixel-level labels to images based on textual descriptions, even for categories beyond predefined closed sets. While vision-language foundation models like CLIP are widely used for this task, fine-tuning them for pixel-level predictions often compromises their generalization capabilities. To address this, we propose a novel fine-tuning strategy, CP-CLIP, which generates customized parameters for CLIP without sacrificing its generalization. Our method employs a customized parameter generator that produces newly added parameters based on random noise, using local visual features from CLIP

BibTeX

@inproceedings{aaai2026_cpclipcustomized,
  title = {CP-CLIP: Customized Parameter Generation for Open-vocabulary Semantic Segmentation},
  author = {Zelin Peng and Zhengqin Xu and Feilong Tang and Wei Shen},
  booktitle = {AAAI 2026},
  year = {2026}
}