cs.AI updates on arXiv.org 16小时前
Separating Knowledge and Perception with Procedural Data
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

本文介绍了一种仅使用程序数据训练的表示模型,其在视觉相似度、分类和语义分割任务中表现出色,并通过视觉记忆数据库实现了对真实图像的全部分隔化。

arXiv:2508.11697v1 Announce Type: cross Abstract: We train representation models with procedural data only, and apply them on visual similarity, classification, and semantic segmentation tasks without further training by using visual memory -- an explicit database of reference image embeddings. Unlike prior work on visual memory, our approach achieves full compartmentalization with respect to all real-world images while retaining strong performance. Compared to a model trained on Places, our procedural model performs within $1\%$ on NIGHTS visual similarity, outperforms by $8\%$ and $15\%$ on CUB200 and Flowers102 fine-grained classification, and is within $10\%$ on ImageNet-1K classification. It also demonstrates strong zero-shot segmentation, achieving an $R^2$ on COCO within $10\%$ of the models trained on real data. Finally, we analyze procedural versus real data models, showing that parts of the same object have dissimilar representations in procedural models, resulting in incorrect searches in memory and explaining the remaining performance gap.

Fish AI Reader

Fish AI Reader

AI辅助创作,多种专业模板,深度分析,高质量内容生成。从观点提取到深度思考,FishAI为您提供全方位的创作支持。新版本引入自定义参数,让您的创作更加个性化和精准。

FishAI

FishAI

鱼阅,AI 时代的下一个智能信息助手,助你摆脱信息焦虑

联系邮箱 441953276@qq.com

相关标签

程序数据训练 视觉任务 模型表现
相关文章