Prototype Mixture Models for Few-shot Semantic Segmentation

2020-08-10 · ECCV 2020 8 · Boyu Yang, Chang Liu, Bohao Li, Jianbin Jiao, Qixiang Ye

Few-shot segmentation is challenging because objects within the support and query images could significantly differ in appearance and pose. Using a single prototype acquired directly from the support image to segment the query image causes semantic ambiguity. In this paper, we propose prototype mixture models (PMMs), which correlate diverse image regions with multiple prototypes to enforce the prototype-based semantic representation. Estimated by an Expectation-Maximization algorithm, PMMs incorporate rich channel-wised and spatial semantics from limited support images. Utilized as representations as well as classifiers, PMMs fully leverage the semantics to activate objects in the query image while depressing background regions in a duplex manner. Extensive experiments on Pascal VOC and MS-COCO datasets show that PMMs significantly improve upon state-of-the-arts. Particularly, PMMs improve 5-shot segmentation performance on MS-COCO by up to 5.82\% with only a moderate cost for model size and inference speed.

📄 PDF Abstract BibTeX arXiv:2008.03898

Code (1)

Yang-Bob/PMMs 공식 구현 pytorch

Tasks

Few-Shot Semantic Segmentation Segmentation Semantic Segmentation

SCNet: Enhancing Few-Shot Semantic Segmentation by Self-Contrastive Background Prototypes

2021-04-19 · Jiacheng Chen, Bin-Bin Gao, Zongqing Lu, Jing-Hao Xue 외

Few-shot semantic segmentation aims to segment novel-class objects in a query image with only a few annotated examples in support images. Most of advanced solutions exploit a metric learning framework that performs segme…

Few-Shot Semantic Segmentation Metric Learning Segmentation Semantic Segmentation

Prototype Adaption and Projection for Few- and Zero-shot 3D Point Cloud Semantic Segmentation

2023-05-23 · Shuting He, Xudong Jiang, Wei Jiang, Henghui Ding

In this work, we address the challenging task of few-shot and zero-shot 3D point cloud semantic segmentation. The success of few-shot semantic segmentation in 2D computer vision is mainly driven by the pre-training on la…

Few-shot 3D semantic segmentation Segmentation

PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment

2019-08-18 · ICCV 2019 10 · Kaixin Wang, Jun Hao Liew, Yingtian Zou, Daquan Zhou 외

Despite the great progress made by deep CNNs in image semantic segmentation, they typically require a large number of densely-annotated images for training and are difficult to generalize to unseen object categories. Few…

Few-Shot Semantic Segmentation Metric Learning Segmentation Semantic Segmentation

ProMi: An Efficient Prototype-Mixture Baseline for Few-Shot Segmentation with Bounding-Box Annotations

2025-05-18 · Florent Chiaroni, Ali Ayub, Ola Ahmad

In robotics applications, few-shot segmentation is crucial because it allows robots to perform complex tasks with minimal training data, facilitating their adaptation to diverse, real-world environments. However, pixel-l…

Part-aware Prototype Network for Few-shot Semantic Segmentation

2020-07-13 · ECCV 2020 8 · Yongfei Liu, Xiangyi Zhang, Songyang Zhang, Xuming He

Few-shot semantic segmentation aims to learn to segment new object classes with only a few annotated examples, which has a wide range of real-world applications. Most existing methods either focus on the restrictive sett…

Few-Shot Semantic Segmentation Graph Neural Network Object Segmentation+2