paper-with-me

홈 › Papers

Spatial Location Constraint Prototype Loss for Open Set Recognition

2021-10-21 · Ziheng Xia, Ganggang Dong, Penghui Wang, Hongwei Liu

One of the challenges in pattern recognition is open set recognition. Compared with closed set recognition, open set recognition needs to reduce not only the empirical risk, but also the open space risk, and the reduction of these two risks corresponds to classifying the known classes and identifying the unknown classes respectively. How to reduce the open space risk is the key of open set recognition. This paper explores the origin of the open space risk by analyzing the distribution of known and unknown classes features. On this basis, the spatial location constraint prototype loss function is proposed to reduce the two risks simultaneously. Extensive experiments on multiple benchmark datasets and many visualization results indicate that our methods is superior to most existing approaches.

📄 PDF Abstract BibTeX arXiv:2110.11013

Code (1)

Xiaziheng89/Spatial-Location-Constraint-Prototype-Loss-for-Open-Set-Recognition 공식 구현 pytorch

Tasks

Open Set Learning

Similar Papers 제목 키워드 기반

ROG$_{PL}$: Robust Open-Set Graph Learning via Region-Based Prototype Learning

2024-02-28 · Qin Zhang, Xiaowei Li, Jiexin Lu, Liping Qiu 외

Open-set graph learning is a practical task that aims to classify the known class nodes and to identify unknown class samples as unknowns. Conventional node classification methods usually perform unsatisfactorily in open…

DenoisingGraph LearningNode ClassificationOpen Set Learning

Adversarial Motorial Prototype Framework for Open Set Recognition

2021-07-13 · Ziheng Xia, Penghui Wang, Ganggang Dong, Hongwei Liu

Open set recognition is designed to identify known classes and to reject unknown classes simultaneously. Specifically, identifying known classes and rejecting unknown classes correspond to reducing the empirical risk and…

Open Set Learning

Multi-Label Prototype Visual Spatial Search for Weakly Supervised Semantic Segmentation

2025-01-01 · CVPR 2025 1 · Songsong Duan, Xi Yang, Nannan Wang

Existing Weakly Supervised Semantic Segmentation (WSSS) relies on the CNN-based Class Activation Map (CAM) and Transformer-based self-attention map to generate class-specific masks for semantic segmentation. However,…

Semantic SegmentationWeakly supervised Semantic SegmentationWeakly-Supervised Semantic Segmentation

A Location-Sensitive Local Prototype Network for Few-Shot Medical Image Segmentation

2021-03-18 · Qinji Yu, Kang Dang, Nima Tajbakhsh, Demetri Terzopoulos 외

Despite the tremendous success of deep neural networks in medical image segmentation, they typically require a large amount of costly, expert-level annotated data. Few-shot segmentation approaches address this issue by l…

Image SegmentationMedical Image SegmentationOrgan SegmentationSegmentation+1

Constrained optimization of sensor placement for nuclear digital twins

2023-06-23 · Niharika Karnik, Mohammad G. Abdo, Carlos E. Estrada Perez, Jun Soo Yoo 외

The deployment of extensive sensor arrays in nuclear reactors is infeasible due to challenging operating conditions and inherent spatial limitations. Strategically placing sensors within defined spatial constraints is es…