MaskDiff: Modeling Mask Distribution with Diffusion Probabilistic Model for Few-Shot Instance Segmentation
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (3) · 2874-2881
DOI: 10.1609/aaai.v38i3.28068 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Minh-Quan Le und 5 weiteren Autor:innen. Die Arbeit wurde bisher 20-mal zitiert (Crossref).
Abstract (Originalsprache)
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.
Zitieren
APA
Le, M., Nguyen, T. V., Le, T., Do, T., Do, M. N., & Tran, M. (2024). MaskDiff: Modeling Mask Distribution with Diffusion Probabilistic Model for Few-Shot Instance Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 38(3), 2874-2881. https://doi.org/10.1609/aaai.v38i3.28068
Vancouver
Le M, Nguyen TV, Le T, Do T, Do MN, Tran M. MaskDiff: Modeling Mask Distribution with Diffusion Probabilistic Model for Few-Shot Instance Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(3):2874-2881. doi:10.1609/aaai.v38i3.28068
BibTeX
@article{Le2024,
author = {Le, Minh-Quan and Nguyen, Tam V. and Le, Trung-Nghia and Do, Thanh-Toan and Do, Minh N. and Tran, Minh-Triet},
title = {MaskDiff: Modeling Mask Distribution with Diffusion Probabilistic Model for Few-Shot Instance Segmentation},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {3},
pages = {2874--2881},
doi = {10.1609/aaai.v38i3.28068}
}
EUVIMED