Diffusion Probabilistic Methods are employed for state-of-the-art image generation. In this work, we present a method for extending such models for performing image segmentation. The method learns end-to-end, without relying on a pre-trained backbone. The information in the input image and in the current estimation of the segmentation map is merged by summing the output of two encoders. Additional encoding layers and a decoder are then used to iteratively refine the segmentation map, using a diffusion model. Since the diffusion model is probabilistic, it is applied multiple times, and the results are merged into a final segmentation map. The new method produces state-of-the-art results on the Cityscapes validation set, the Vaihingen building segmentation benchmark, and the MoNuSeg dataset.
翻译:用于最先进的图像生成的集成概率方法 。 在此工作中, 我们展示了一种扩展图像分割模型的方法 。 该方法在不依赖受过训练的脊柱的情况下, 学习端到端。 输入图像中的信息和目前对分解图的估计信息通过对两个编码器的输出值进行映射而合并。 然后使用一个扩散模型, 使用额外的编码层和一个解码器来迭接精细化分解图 。 由于扩散模型具有概率性, 它被多次应用, 结果被合并到最后的分解图中。 新方法在城市景验证集、 Viiihingen 建筑分解基准和 MoNuSeg 数据集上产生最先进的结果 。