SegGen：利用Text2Mask与Mask2Img合成增强分割模型
SegGen: Supercharging Segmentation Models with Text2Mask and Mask2Img Synthesis
AI总结：
本文提出SegGen数据生成方法，通过MaskSyn和ImgSyn两种策略合成多样化掩码-图像对，在ADE20K和COCO上显著提升语义、全景及实例分割模型性能，并增强模型对未见领域的鲁棒性。
摘要：
我们提出SegGen，一种高效的图像分割训练数据生成方法，该方法在显著程度上推动了最先进分割模型的性能极限。SegGen设计并整合了两种数据生成策略：MaskSyn和ImgSyn。（i）MaskSyn通过我们提出的文本到掩码生成模型和掩码到图像生成模型合成新的掩码-图像对，极大地提高了用于模型监督的分割掩码多样性；（ii）ImgSyn利用掩码到图像生成模型基于现有掩码合成新图像，有力地提升了模型输入的图像多样性。在竞争激烈的ADE20K和COCO基准上，我们的数据生成方法在语义分割、全景分割和实例分割中显著改善了最先进分割模型的性能。值得注意的是，在ADE20K mIoU指标上，Mask2Former R50从47.2大幅提升至49.9（+2.7）；Mask2Former Swin-L也从56.1显著提升至57.4（+1.3）。这些令人鼓舞的结果有力地证明了即使在使用大量人工标注训练数据的情况下，我们的SegGen依然有效。此外，使用我们的合成数据进行训练使分割模型对未见领域更加鲁棒。项目网站：https://seggenerator.github.io
英文摘要：
We propose SegGen, a highly-effective training data generation method for image segmentation, which pushes the performance limits of state-of-the-art segmentation models to a significant extent. SegGen designs and integrates two data generation strategies: MaskSyn and ImgSyn. (i) MaskSyn synthesizes new mask-image pairs via our proposed text-to-mask generation model and mask-to-image generation model, greatly improving the diversity in segmentation masks for model supervision; (ii) ImgSyn synthesizes new images based on existing masks using the mask-to-image generation model, strongly improving image diversity for model inputs. On the highly competitive ADE20K and COCO benchmarks, our data generation method markedly improves the performance of state-of-the-art segmentation models in semantic segmentation, panoptic segmentation, and instance segmentation. Notably, in terms of the ADE20K mIoU, Mask2Former R50 is largely boosted from 47.2 to 49.9 (+2.7); Mask2Former Swin-L is also significantly increased from 56.1 to 57.4 (+1.3). These promising results strongly suggest the effectiveness of our SegGen even when abundant human-annotated training data is utilized. Moreover, training with our synthetic data makes the segmentation models more robust towards unseen domains. Project website: https://seggenerator.github.io
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
