UE-CLIP: Entropy-Guided Adaptive Prompt Sparsification for Efficient Open-Vocabulary Semantic Segmentation
编号:183 访问权限:仅限参会人 更新:2026-11-15 17:48:35 浏览:17次 In-person

报告开始:2026年11月20日 13:45(Asia/Kolkata)

报告时间:15min

所在会场:[S4] Artificial Intelligence and Intelligent Computing [S4-1] Artificial Intelligence and Intelligent Computing

演示文件 附属文件

提示:该报告下的文件权限为仅限参会人,您尚未登录,暂时无法查看。

摘要
Open vocabulary semantic segmentation applies the dense prediction paradigm to the open-vocabulary setting using the knowledge about the categories contained in the visionlanguage models like the CLIP model. However, in most existing segmentation methods based on CLIP, the computational cost of prompt generation remains constant for each individual image but might vary across different categories out of which only some are relevant for that specific image. In this paper, we study the task of prompt selection as a form of dynamic allocation of resources and introduce our proposed method, Uncertainty-Entropy Guided CLIP (UE-CLIP). UE-CLIP uses the pre-trained CLIP ViT-L/14-336 image encoder and a class presence head. Prompt selection for the cross-attention is guided by binary Shannon entropy and a threshold that can be learned, hence selecting the most relevant and confident prompts. The selected prompts yield confidence-weighted scene tokens that get aggregated along with the visual feature after refinement through ViT-Adapter and decoding through UperNet. On the ADE20K dataset, UE-CLIP attains CLIP-SP mIoU level (51.89%) and demonstrates 76.7% reduction of the number of active prompts from 30 to 7.0 and 0.23× cost compared to 1.00×.
关键词
暂无
报告人
Ameena Naik
STUDENT SGBIT

Salika Khatib
STUDENT SGBIT

稿件作者
Ameena Naik SGBIT
Salika Khatib SGBIT
Hemant Darur Kle University
发表评论
验证码 看不清楚,更换一张
全部评论
重要日期
  • 会议日期

    11月20日

    2026

    至

    11月22日

    2026

  • 10月31日 2026

    初稿截稿日期

  • 11月07日 2026

    提前注册日期

  • 11月22日 2026

    注册截止日期

主办单位
United Societies of Science
承办单位
Pondicherry University
协办单位
IEEE Section
IEEE Madras Section
移动端
在手机上打开
小程序
打开微信小程序
客服
扫码或点此咨询