论文标题
扩散量：实例分割的扩散模型
DiffusionInst: Diffusion Model for Instance Segmentation
论文作者
论文摘要
与先前最先进的图像生成模型相比，扩散框架的性能可比性。研究人员对其在判别任务中的变体感到好奇，因为它具有强大的噪声到图像降解管道。本文提出了扩散式，这是一个新颖的框架，将实例表示为实例感知过滤器，并将实例分割为噪声到过滤器的变形型过程。该模型经过训练，可以逆转嘈杂的地面图，而没有RPN的任何感应偏置。在推断期间，它将随机生成的过滤器作为输入，并以一步或多步降解输出掩码。对可可和LVIS的广泛实验结果表明，与现有的实例分割模型相比，扩散性能具有竞争性能，例如Resnet和Swin Transformers。我们希望我们的工作能够充当强大的基线，这可以激发设计更有效的扩散框架，以挑战歧视性任务。我们的代码可在https://github.com/chenhaoxing/diffusioninst中找到。
Diffusion frameworks have achieved comparable performance with previous state-of-the-art image generation models. Researchers are curious about its variants in discriminative tasks because of its powerful noise-to-image denoising pipeline. This paper proposes DiffusionInst, a novel framework that represents instances as instance-aware filters and formulates instance segmentation as a noise-to-filter denoising process. The model is trained to reverse the noisy groundtruth without any inductive bias from RPN. During inference, it takes a randomly generated filter as input and outputs mask in one-step or multi-step denoising. Extensive experimental results on COCO and LVIS show that DiffusionInst achieves competitive performance compared to existing instance segmentation models with various backbones, such as ResNet and Swin Transformers. We hope our work could serve as a strong baseline, which could inspire designing more efficient diffusion frameworks for challenging discriminative tasks. Our code is available in https://github.com/chenhaoxing/DiffusionInst.
