MagicSeg: Open-World Segmentation Pretraining via Counterfactural Diffusion-Based Auto-Generation

ArXi:2603.19575v1 Announce Type: new Open-world semantic segmentation presently relies significantly on extensive image-text pair datasets, which often suffer from a lack of fine-grained pixel annotations on sufficient categories. The acquisition of such data is rendered economically prohibitive due to the substantial investments of both human labor and time. In light of the formidable image generation capabilities of diffusion models, we