Journal ArticleMaskDiff: Modeling Mask Distribution with Diffusion Probabilistic Model for Few-Shot Instance SegmentationLe, Minh-Quan; Nguyen, Tam V; Le, Trung-Nghia; Do, Thanh-Toan; Do, Minh N; Tran, Minh-TrietFew-shot instance segmentation extends the few-shot learning paradigm to the instance segmentation task, which tries to segment instance objects from a query image with a few annotated examples of novel categories. Conventional approaches have attempted to address the task via prototype learning, known as point estimation. However, this mechanism depends on prototypes (e.g. mean of K-shot) for prediction, leading to performance instability. To overcome the disadvantage of the point estimation mechanism, we propose a novel approach, dubbed MaskDiff, which models the underlying conditional distribution of a binary mask, which is conditioned on an object region and K-shot information. Inspired by augmentation approaches that perturb data with Gaussian noise for populating low data density regions, we model the mask distribution with a diffusion probabilistic model. We also propose to utilize classifier-free guided mask sampling to integrate category information into the binary mask generation process. Without bells and whistles, our proposed method consistently outperforms state-of-the-art methods on both base and novel classes of the COCO dataset while simultaneously being more stable than existing methods. The source code is available at: https://github.com/minhquanlecs/MaskDiff.AAAI2024-03-2510521808Proceedings of the AAAI Conference on Artificial Intelligence3832874 to 28812159-5399https://doi.org/10.1609/aaai.v38i3.280682025234SegmentationDeep Generative Models & AutoencodersNational Science Foundation