{"ID":5936985,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-09T15:38:11.834581458Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.05253","arxiv_id":"2607.05253","title":"Repurposing CLIP to Localize at Pixel Level","abstract":"Large-scale Vision-Language Models like CLIP have demonstrated impressive open-set localization capabilities at the image level. However, adapting this capability to pixel-level dense prediction poses challenges due to global feature biases. In this paper, we introduce CLIPix, a simple yet effective framework that repurposes CLIP to perform pixel-level localization. By tracing back CLIP's classification process, CLIPix identifies object-specific attentive regions and repurposes them as pixel-level localization cues. To address noise introduced by global biases, we propose a Noise-Resistant Correction strategy, refining these cues for more precise segmentation. Additionally, we introduce a Localization Embedding strategy to integrate both localization and enriched detail information, enabling accurate, high-resolution segmentation. Our approach preserves CLIP's generalization strength and unlocks its potential for segmenting arbitrary objects. Extensive experiments on the PASCAL and COCO datasets demonstrate that CLIPix achieves state-of-the-art performance, underscoring its effectiveness.","short_abstract":"Large-scale Vision-Language Models like CLIP have demonstrated impressive open-set localization capabilities at the image level. However, adapting this capability to pixel-level dense prediction poses challenges due to global feature biases. In this paper, we introduce CLIPix, a simple yet effective framework that repu...","url_abs":"https://arxiv.org/abs/2607.05253","url_pdf":"https://arxiv.org/pdf/2607.05253v1","authors":"[\"Jiaxiang Fang\",\"Shiqiang Ma\",\"Jing Wang\",\"Siyu Chen\",\"Fei Guo\",\"Shengfeng He\"]","published":"2026-07-06T16:00:17Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Language Model\"]","has_code":false}