Skip to yearly menu bar Skip to main content


DetDiffusion: Synergizing Generative and Perceptive Models for Enhanced Data Generation and Perception

Yibo Wang · Ruiyuan Gao · Kai Chen · Kaiqiang Zhou · Yingjie CAI · Lanqing Hong · Zhenguo Li · Lihui Jiang · Dit-Yan Yeung · Qiang Xu · Kai Zhang

Arch 4A-E Poster #238
[ ]
Wed 19 Jun 5 p.m. PDT — 6:30 p.m. PDT


Current perceptive models heavily depend on resource-intensive datasets, prompting the need for innovative solutions. Leveraging recent advances in diffusion models, synthetic data, by constructing image inputs from various annotations, proves beneficial for downstream tasks. While prior methods have separately addressed generative and perceptive models, DetDiffusion, for the first time, harmonizes both, tackling the challenges in generating effective data for perceptive models. To enhance image generation with perceptive models, we introduce perception-aware loss (P.A. loss) through segmentation, improving both quality and controllability. To boost the performance of specific perceptive models, our method customizes data augmentation by extracting and utilizing perception-aware attribute (P.A. Attr) during generation. Experimental results from the object detection task highlight DetDiffusion's superior performance, establishing a new state-of-the-art in layout-guided generation. Furthermore, image syntheses from DetDiffusion can effectively augment training data, significantly enhancing downstream detection performance.

Live content is unavailable. Log in and register to view live content