@article{761,
  keywords = {Segmentation, Deep Generative Models & Autoencoders},
  author = {Minh-Quan Le and Tam Nguyen and Trung-Nghia Le and Thanh-Toan Do and Minh Do and Minh-Triet Tran},
  title = {MaskDiff: Modeling Mask Distribution with Diffusion Probabilistic Model for Few-Shot Instance Segmentation},
  abstract = {Few-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.},
  year = {2024},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  volume = {38},
  chapter = {2874},
  pages = {8},
  month = {03},
  publisher = {AAAI},
  issn = {2159-5399},
  url = {https://par.nsf.gov/biblio/10521808},
  doi = {10.1609/aaai.v38i3.28068},
}