MaskDiff: Modeling Mask Distribution with Diffusion Probabilistic Model for Few-Shot Instance Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Le, Minh-Quan, Nguyen, Tam V., Le, Trung-Nghia, Do, Thanh-Toan, Do, Minh N., Tran, Minh-Triet
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910303485165568
author Le, Minh-Quan
Nguyen, Tam V.
Le, Trung-Nghia
Do, Thanh-Toan
Do, Minh N.
Tran, Minh-Triet
author_facet Le, Minh-Quan
Nguyen, Tam V.
Le, Trung-Nghia
Do, Thanh-Toan
Do, Minh N.
Tran, Minh-Triet
contents 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 (\eg 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.
format Preprint
id arxiv_https___arxiv_org_abs_2303_05105
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle MaskDiff: Modeling Mask Distribution with Diffusion Probabilistic Model for Few-Shot Instance Segmentation
Le, Minh-Quan
Nguyen, Tam V.
Le, Trung-Nghia
Do, Thanh-Toan
Do, Minh N.
Tran, Minh-Triet
Computer Vision and Pattern Recognition
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 (\eg 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.
title MaskDiff: Modeling Mask Distribution with Diffusion Probabilistic Model for Few-Shot Instance Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2303.05105