DIVE: Inverting Conditional Diffusion Models for Discriminative Tasks
文献类型：期刊论文
| 作者 | Li, Yinqi1,2; Chang, Hong1,2; Hou, Ruibing1; Shan, Shiguang1,2; Chen, Xilin1,2 |
| 刊名 | IEEE TRANSACTIONS ON MULTIMEDIA
 |
| 出版日期 | 2026 |
| 卷号 | 28页码:297-308 |
| 关键词 | Diffusion models Object detection Layout Noise Training Noise reduction Vocabulary Dogs Bicycles Image synthesis Diffusion model generative modeling discriminative Task object detection visual recognition |
| ISSN号 | 1520-9210 |
| DOI | 10.1109/TMM.2025.3623508 |
| 英文摘要 | Diffusion models have shown remarkable progress in various generative tasks such as image and video generation. This paper studies the problem of leveraging pretrained diffusion models for performing discriminative tasks. Specifically, we extend the discriminative capability of pretrained frozen generative diffusion models from the classification task (Li et al., 2023), (Clark et al., 2023) to the more complex object detection task, by "inverting" a pretrained layout-to-image diffusion model. To this end, a gradient-based discrete optimization approach for replacing the heavy prediction enumeration process, and a prior distribution model for making more accurate use of the Bayes' rule, are proposed respectively. Empirical results show that this method is on par with basic discriminative object detection baselines on COCO dataset. In addition, our method can greatly speed up the previous diffusion-based method (Li et al., 2023), (Clark et al., 2023) for classification without sacrificing accuracy. Code and models are available at https://github.com/LiYinqi/DIVE. |
| 资助项目 | National Natural Science Foundation of China (NSFC)[62376259] ; National Natural Science Foundation of China (NSFC)[62306301] ; National Postdoctoral Program for Innovative Talents[BX20220310] |
| WOS研究方向 | Computer Science ; Telecommunications |
| 语种 | 英语 |
| WOS记录号 | WOS:001658631000033 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 源URL | [http://119.78.100.204/handle/2XEOYT63/42841]  |
| 专题 | 中国科学院计算技术研究所 |
| 通讯作者 | Chang, Hong |
| 作者单位 | 1.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China |
| 推荐引用方式 GB/T 7714 | Li, Yinqi,Chang, Hong,Hou, Ruibing,et al. DIVE: Inverting Conditional Diffusion Models for Discriminative Tasks[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2026,28:297-308. |
| APA | Li, Yinqi,Chang, Hong,Hou, Ruibing,Shan, Shiguang,&Chen, Xilin.(2026).DIVE: Inverting Conditional Diffusion Models for Discriminative Tasks.IEEE TRANSACTIONS ON MULTIMEDIA,28,297-308. |
| MLA | Li, Yinqi,et al."DIVE: Inverting Conditional Diffusion Models for Discriminative Tasks".IEEE TRANSACTIONS ON MULTIMEDIA 28(2026):297-308. |
入库方式： OAI收割
来源：计算技术研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。