paper-with-me

홈 › Papers

Open-set learning with augmented categories by exploiting unlabelled data

2020-02-04 · Emile R. Engelbrecht, Johan A. du Preez

Novel categories are commonly defined as those unobserved during training but present during testing. However, partially labelled training datasets can contain unlabelled training samples that belong to novel categories, meaning these can be present in training and testing. This research is the first to generalise between what we call observed-novel and unobserved-novel categories within a new learning policy called open-set learning with augmented category by exploiting unlabelled data or Open-LACU. After surveying existing learning policies, we introduce Open-LACU as a unified policy of positive and unlabelled learning, semi-supervised learning and open-set recognition. Subsequently, we develop the first Open-LACU model using an algorithmic training process of the relevant research fields. The proposed Open-LACU classifier achieves state-of-the-art and first-of-its-kind results.

📄 PDF Abstract BibTeX arXiv:2002.01368

Code (0)

등록된 구현이 없습니다.

Tasks

General ClassificationNovelty Detectionobject-detectionObject DetectionOpen Set LearningSemantic Segmentation

Similar Papers 제목 키워드 기반

CiPR: An Efficient Framework with Cross-instance Positive Relations for Generalized Category Discovery

2023-04-14 · Shaozhe Hao, Kai Han, Kwan-Yee K. Wong

We tackle the issue of generalized category discovery (GCD). GCD considers the open-world problem of automatically clustering a partially labelled dataset, in which the unlabelled data may contain instances from both nov…

ClusteringContrastive LearningRepresentation Learning

HydraMix-Net: A Deep Multi-task Semi-supervised Learning Approach for Cell Detection and Classification

2020-08-11 · R. M. Saad Bashir, Talha Qaiser, Shan E Ahmed Raza, Nasir M. Rajpoot

Semi-supervised techniques have removed the barriers of large scale labelled set by exploiting unlabelled data to improve the performance of a model. In this paper, we propose a semi-supervised deep multi-task classifica…

Cell DetectionGeneral ClassificationMulti-Task Learning

Class-incremental Novel Class Discovery

2022-07-18 · Subhankar Roy, Mingxuan Liu, Zhun Zhong, Nicu Sebe 외

We study the new task of class-incremental Novel Class Discovery (class-iNCD), which refers to the problem of discovering novel categories in an unlabelled data set by leveraging a pre-trained model that has been trained…

Incremental LearningKnowledge DistillationNovel Class Discovery

Simplifying Open-Set Video Domain Adaptation with Contrastive Learning

2023-01-09 · Giacomo Zara, Victor Guilherme Turrisi da Costa, Subhankar Roy, Paolo Rota 외

In an effort to reduce annotation costs in action recognition, unsupervised video domain adaptation methods have been proposed that aim to adapt a predictive model from a labelled dataset (i.e., source domain) to an unla…

Action RecognitionContrastive LearningDomain Adaptation

TUGAS: Exploiting unlabelled data for Twitter sentiment analysis

2014-08-01 · SEMEVAL 2014 8 · Silvio Amir, Miguel B. Almeida, Bruno Martins, Jo{\~a}o Filgueiras 외
Sentiment AnalysisTwitter Sentiment Analysis