paper-with-me

Papers

Prototype Fission: Closing Set for Robust Open-set Semi-supervised Learning

2023-08-29 · Xuwei Tan, Yi-Jie Huang, Yaqian Li

Semi-supervised Learning (SSL) has been proven vulnerable to out-of-distribution (OOD) samples in realistic large-scale unsupervised datasets due to over-confident pseudo-labeling OODs as in-distribution (ID). A key underlying problem is class-wise latent space spreading from closed seen space to open unseen space, and the bias is further magnified in SSL's self-training loops. To close the ID distribution set so that OODs are better rejected for safe SSL, we propose Prototype Fission(PF) to divide class-wise latent spaces into compact sub-spaces by automatic fine-grained latent space mining, driven by coarse-grained labels only. Specifically, we form multiple unique learnable sub-class prototypes for each class, optimized towards both diversity and consistency. The Diversity Modeling term encourages samples to be clustered by one of the multiple sub-class prototypes, while the Consistency Modeling term clusters all samples of the same class to a global prototype. Instead of "opening set", i.e., modeling OOD distribution, Prototype Fission "closes set" and makes it hard for OOD samples to fit in sub-class latent space. Therefore, PF is compatible with existing methods for further performance gains. Extensive experiments validate the effectiveness of our method in open-set SSL settings in terms of successfully forming sub-classes, discriminating OODs from IDs and improving overall accuracy. Codes will be released.

📄 PDF Abstract BibTeX arXiv:2308.15575

Code (0)

등록된 구현이 없습니다.

Tasks

Diversity

Similar Papers 제목 키워드 기반

Open-world Semi-supervised Novel Class Discovery

2023-05-22 · Jiaming Liu, Yangqiming Wang, Tongze Zhang, Yulu Fan 외

Traditional semi-supervised learning tasks assume that both labeled and unlabeled data follow the same class distribution, but the realistic open-world scenarios are of more complexity with unknown novel classes mixed in…

Contrastive LearningNovel Class DiscoveryRepresentation Learning

Distribution Prototype Diffusion Learning for Open-set Supervised Anomaly Detection

2025-01-01 · CVPR 2025 1 · Fuyun Wang, Tong Zhang, Yuanzhi Wang, Yide Qiu 외

In Open-set Supervised Anomaly Detection (OSAD), the existing methods typically generate pseudo anomalies to compensate for the scarcity of observed anomaly samples, while overlooking critical priors of normal sam…

Anomaly DetectionSupervised Anomaly Detection

Prompt-Driven Feature Diffusion for Open-World Semi-Supervised Learning

2024-04-17 · Marzi Heidari, Hanping Zhang, Yuhong Guo

In this paper, we present a novel approach termed Prompt-Driven Feature Diffusion (PDFD) within a semi-supervised learning framework for Open World Semi-Supervised Learning (OW-SSL). At its core, PDFD deploys an efficien…

Open-World Semi-Supervised LearningRepresentation Learning

POWN: Prototypical Open-World Node Classification

2024-06-14 · Marcel Hoffmann, Lukas Galke, Ansgar Scherp

We consider the problem of \textit{true} open-world semi-supervised node classification, in which nodes in a graph either belong to known or new classes, with the latter not present during training. Existing methods dete…

ClassificationData AugmentationNode ClassificationSelf-Supervised Learning

The Others: Naturally Isolating Out-of-Distribution Samples for Robust Open-Set Semi-Supervised Learning

2025-04-17 · You Rim Choi, Subeom Park, Seojun Heo, Eunchung Noh 외

Open-Set Semi-Supervised Learning (OSSL) tackles the practical challenge of learning from unlabeled data that may include both in-distribution (ID) and unknown out-of-distribution (OOD) classes. However, existing OSSL me…

Contrastive Learning