.png){kind=icon}
返回
Attentional prototype inference for few-shot segmentation
.png){kind=icon}
OA
AI
DOI：10.1016/j.patcog.2023.109726.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This paper aims to address few-shot segmentation. While existing prototype-based methods have achieved considerable success, they suffer from uncertainty and ambiguity caused by limited labeled ex-amples. In this work, we propose attentional prototype inference (API), a probabilistic latent variable framework for few-shot segmentation. We define a global latent variable to represent the prototype of each object category, which we model as a probabilistic distribution. The probabilistic modeling of the prototype enhances the model's generalization ability by handling the inherent uncertainty caused by limited data and intra-class variations of objects. To further enhance the model, we introduce a local la-tent variable to represent the attention map of each query image, which enables the model to attend to foreground objects while suppressing the background. The optimization of the proposed model is formu-lated as a variational Bayesian inference problem, which is established by amortized inference networks. We conduct extensive experiments on four benchmarks, where our proposal obtains at least competitive and often better performance than state-of-the-art prototype-based methods. We also provide compre-hensive analyses and ablation studies to gain insight into the effectiveness of our method for few-shot segmentation.& COPY; 2023 Published by Elsevier Ltd.
Keyword:
Few -shot segmentation
Variational inference
Probabilistic model
Latent attention
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
GPNet: Gated pyramid network for semantic segmentationGPNet: 用于语义分割的门控金字塔网络.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏The Lung Image Database Consortium, (LIDC) and Image Database Resource Initiative (IDRI): A Completed Reference Database of Lung Nodules on CT Scans肺图像数据库联盟 (LIDC) 和图像数据库资源倡议 (IDRI): ct扫描上完整的肺结节参考数据库MEDICAL PHYSICS
OAAI
MEDICAL PHYSICSIF3.2
OAAI分享收藏Meta-seg: A survey of meta-learning for image segmentationMeta-seg: 图像分割的元学习综述PATTERN RECOGNITIONOAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏Few-shot prototype alignment regularization network for document image layout segementationPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Variational posterior approximation using stochastic gradient ascent with adaptive stepsizePATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏
查看更多内容