Symmetrical Joint Learning Support-query Prototypes for Few-shot Segmentation
School of Computer Science, Nanjing University of Posts and Telecommunications（南京邮电大学计算机学院）；Singapore University of Technology and Design（新加坡科技设计大学）；School of Artificial Intelligence, Beijing University of Posts and Telecommunications（北京邮电大学人工智能学院）；University of California at Riverside（加州大学河滨分校）
Qun Li, Baoquan Sun, Fu Xiao, Yonggang Qi, Bir Bhanu
We propose Sym-Net, a novel framework for Few-Shot Segmentation (FSS) that addresses the critical issue of intra-class variation by jointly learning both query and support prototypes in a symmetrical manner. Unlike previous methods that generate query prototypes solely by matching query features to support prototypes, which is a form of bias learning towards the few-shot support samples, Sym-Net leverages a balanced symmetrical learning approach for both query and support prototypes, ensuring that the learning process does not favor one set (support or query) over the other. One of main modules of Sym-Net is the visual-text alignment-based prototype aggregation module, which is not just query-guided prototype refinement, it is a jointly learning from both support and query samples, which makes the model beneficial for handling intra-class discrepancies and allows it to generalize better to new, unseen classes. Specifically, a parameter-free prior mask generation module is designed to accurately localize both local and global regions of the query object by using sliding windows of different sizes and a self-activation kernel to suppress incorrect background matches. Additionally, to address the information loss caused by spatial pooling during prototype learning, a top-down hyper-correlation module is integrated to capture multi-scale spatial relationships between support and query images. This approach is further jointly optimized by implementing a co-optimized hard triplet mining strategy. Experimental results show that the proposed Sym-Net outperforms state-of-the-art models, which demonstrates that jointly learning support-query prototypes in a symmetrical manner for FSS offers a promising direction to enhance segmentation performance with limited annotated data.
Query-guided Prototype Evolution Network for Few-Shot Segmentation
Institute of Information Science, Beijing Jiaotong University（北京交通大学信息科学研究所）；School of Control Science and Engineering, Shandong University（山东大学控制科学与工程学院）；School of Computer Science and Technology, University of Chinese Academy of Sciences（中国科学院大学计算机科学与技术学院）；Department of Computer Science, City University of Hong Kong（香港城市大学计算机科学系）
SPENet: Self-guided Prototype Enhancement Network for Few-shot Medical Image Segmentation
School of Computer Science, Beijing University of Technology, Beijing, China（北京理工大学计算机科学学院）；Institute of Automation Chinese Academy of Sciences, Beijing, China（中国科学院自动化研究所）；Multimedia Department Xiaomi Inc, Beijing, China（小米公司多媒体部门）；Capital Medical University Affiliated Beijing Friendship Hospital, Beijing, China（首都医科大学附属北京友谊医院）
Boosting Few-shot 3D Point Cloud Segmentation via Query-Guided Enhancement
Harbin Institute of Technology Shenzhen（哈尔滨工业大学深圳校区）；SmartMore（思谋科技）；Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies（广东省新型安全智能技术重点实验室）
Dynamic Prototype Convolution Network for Few-Shot Semantic Segmentation
Nanjing University of Science and Technology（南京理工大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；University of Amsterdam（阿姆斯特丹大学）；Northeastern University（东北大学）；The Netherlands Cancer Institute（荷兰癌症研究所）
Few to Big: Prototype Expansion Network via Diffusion Learner for Point Cloud Few-shot Semantic Segmentation
School of Mathematics and Computational Science, Xiangtan University（湘潭大学数学与计算科学学院）；School of Automation and Electronics Information, Xiangtan University（湘潭大学自动化与电子信息学院）；School of Automation, Shanghai Jiao Tong University（上海交通大学自动化学院）
Prototype as Query for Few Shot Semantic Segmentation
Northwestern Polytechnical University（西北工业大学）；Suzhou Zhito Technology Co., Ltd（苏州智途科技有限公司）；Ping An Property & Casualty Insurance Company of China Ltd（中国平安财产保险股份有限公司）
Uncertainty-Aware Semi-Supervised Few Shot Segmentation
DGIST（大邱庆北科学技术院）
Few Shot分割（FSS）的目的是学习像素级分类的目标对象在查询图像中使用只有少量的注释支持样本。这是具有挑战性的，因为它需要建模目标对象的外观变化和查询和支持图像之间的不同视觉线索与有限的信息。为了解决这个问题，我们提出了一个半监督的FSS策略，利用额外的原型从未标记的图像与不确定性指导的伪标签细化。为了从未标记的图像中获得可靠的原型，我们对神经网络进行元训练，以联合预测分割并估计预测的不确定性。我们采用不确定性估计来排除具有高度不确定性的伪标签构造的预测，以基于改进的伪标签获得额外的原型。在推理过程中，查询分割预测使用原型从支持和未标记的图像，包括低级别的功能的查询图像。我们的方法是端到端的，可以很容易地补充现有的方法，而不需要额外的训练来使用未标记的样本。在PASCAL- $5^i$和COCO- $20^i$上的大量实验表明，我们的模型可以有效地去除不可靠的预测，以改进伪标签，并显着提高最先进的性能。
Multi-grained Temporal Prototype Learning for Few-shot Video Object Segmentation
Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Northwestern Polytechnical University（西北工业大学）；National University of Singapore（新加坡国立大学）；Australian National University（澳大利亚国立大学）；Linköping University（林雪平大学）
What Do Scan-Derived Class Prototypes Add? Disentangling Supervision, Prototype Content and Query Protocol in Recognition over Frozen Foundation Features
Semantically Meaningful Class Prototype Learning for One-Shot Image Semantic Segmentation
School of Computer Science and Engineering, Nanjing University of Science and Technology（南京理工大学计算机科学与工程学院）；Inception Institute of Artificial Intelligence（Inception人工智能研究院）；School of Computer Science and Engineering, University of Electronic Science and Technology of China（电子科技大学计算机科学与工程学院）
Beyond Euclidean Prototypes: Spectral Disentanglement and Geodesic Matching for Few-Shot Medical Image Segmentation
School of Microelectronics and Communication Engineering, Chongqing University（重庆大学微电子与通信工程学院）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）
IPEC: Test-Time Incremental Prototype Enhancement Classifier for Few-Shot Learning
College of Intelligent Robotics and Advanced Manufacturing, Fudan University（智能机器人与先进制造学院，复旦大学）；School of Microelectronics, Fudan University（微电子学院，复旦大学）；Key Laboratory of Advanced Control and Optimization for Chemical Processes of Ministry of Education, East China University of Science and Technology（教育部先进化工过程控制与优化重点实验室，东华大学）
