Diffusioninst: Diffusion Model for Instance Segmentation
Zhangxuan Gu, Haoxing Chen, Zhuoer Xu
Abstract
Diffusion frameworks have achieved comparable performance with previous state-of-the-art image generation models. This paper proposes DiffusionInst, a novel framework representing instances as vectors and formulates instance segmentation as a noise-to-vector denoising process. The model is trained to reverse the noisy groundtruth mask without any inductive bias from RPN. It takes a randomly generated vector as input and outputs mask with multi-step denoising during inference. Extensive experimental results on COCO and LVIS show that DiffusionInst achieves competitive performance. Our code is available at https://github.com/chenhaoxing/DiffusionInst.
Topics & Concepts
Computer scienceNoise reductionSegmentationInferenceNoise (video)Code (set theory)Artificial intelligenceProcess (computing)Pattern recognition (psychology)Image denoisingDiffusionImage segmentationImage (mathematics)AlgorithmProgramming languageSet (abstract data type)PhysicsThermodynamicsAdvanced Neural Network ApplicationsDomain Adaptation and Few-Shot LearningAdvanced Image and Video Retrieval Techniques