DetDiffusion: Synergizing Generative and Perceptive Models for Enhanced Data Generation and Perception
This work addresses the resource-intensive data dependency problem for perceptive models in computer vision, offering a novel integration that improves data generation and augmentation, though it appears incremental in combining existing approaches.
The paper tackles the challenge of generating effective synthetic data for perceptive models by synergizing generative and perceptive models, introducing perception-aware loss and attributes to improve quality and controllability, resulting in state-of-the-art performance in layout-guided generation and significant enhancement in downstream detection tasks.
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.