paper-with-me

홈 › Papers

Unseen Class Discovery in Open-world Classification

2018-01-17 · ICLR 2018 1 · Lei Shu, Hu Xu, Bing Liu

This paper concerns open-world classification, where the classifier not only needs to classify test examples into seen classes that have appeared in training but also reject examples from unseen or novel classes that have not appeared in training. Specifically, this paper focuses on discovering the hidden unseen classes of the rejected examples. Clearly, without prior knowledge this is difficult. However, we do have the data from the seen training classes, which can tell us what kind of similarity/difference is expected for examples from the same class or from different classes. It is reasonable to assume that this knowledge can be transferred to the rejected examples and used to discover the hidden unseen classes in them. This paper aims to solve this problem. It first proposes a joint open classification model with a sub-model for classifying whether a pair of examples belongs to the same or different classes. This sub-model can serve as a distance function for clustering to discover the hidden classes of the rejected examples. Experimental results show that the proposed model is highly promising.

📄 PDF Abstract BibTeX arXiv:1801.05609

Code (1)

leishu02/EMNLP2017_DOC

Tasks

ClassificationClusteringGeneral Classification

Similar Papers 제목 키워드 기반

Cross-domain Open-world Discovery

2024-06-17 · Shuo Wen, Maria Brbic

In many real-world applications, test data may commonly exhibit categorical shifts, characterized by the emergence of novel classes, as well as distribution shifts arising from feature distributions different from the on…

image-classificationImage Classification

Novel Class Discovery for Open Set Raga Classification

2024-11-27 · Parampreet Singh, Adwik Gupta, Vipul Arora

The task of Raga classification in Indian Art Music (IAM) is constrained by the limited availability of labeled datasets, resulting in many Ragas being unrepresented during the training of machine learning models. Tradit…

ClassificationContrastive LearningInformation RetrievalMusic Information Retrieval+1

OpenGCD: Assisting Open World Recognition with Generalized Category Discovery

2023-08-14 · Fulin Gao, Weimin Zhong, Zhixing Cao, Xin Peng 외

A desirable open world recognition (OWR) system requires performing three tasks: (1) Open set recognition (OSR), i.e., classifying the known (classes seen during training) and rejecting the unknown (unseen$/$novel classe…

Continual LearningDiversityIncremental LearningOpen Set Learning

Hyperbolic Multimodal Representation Learning for Biological Taxonomies

2025-08-22 · ZeMing Gong, Chuanqi Tang, Xiaoliang Huo, Nicholas Pellegrino 외 arxiv

Taxonomic classification in biodiversity research involves organizing biological specimens into structured hierarchies based on evidence, which can come from multiple modalities such as images and genetic information. We…

Representation Learning

Category Discovery: An Open-World Perspective

2025-09-26 · Zhenqi He, Yuanpei Liu, Kai Han arxiv

Category discovery (CD) is an emerging open-world learning task, which aims at automatically categorizing unlabelled data containing instances from unseen classes, given some labelled data from seen classes. This task ha…

Representation Learning