Multi-Label Learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 1
- 보존된 평가 기록
- 1
Multi-label learning (MLL) is a generalization of the binary and multi-category classification problems and deals with tagging a data instance with several possible class labels simultaneously [1]. Each of the assigned labels conveys a specific semantic relationship with the multi-label data instance [2, 3]. Multi-label learning has continued to receive a lot of research interest due to its practical application in many real-world problems such as recommender systems [4], image annotation [5], and text classification [6].
References:
Kumar, S., Rastogi, R., Low rank label subspace transformation for multi-label learning with missing labels. Information Sciences 596, 53–72 (2022)
Zhang M-L, Zhou Z-H (2013) A review on multi-label learning algorithms. IEEE Trans Knowl Data Eng 26(8):1819–1837
Gibaja E, Ventura S (2015) A tutorial on multilabel learning. ACM Comput Surveys (CSUR) 47(3):1–38
Bogaert M, Lootens J, Van den Poel D, Ballings M (2019) Evaluating multi-label classifiers and recommender systems in the financial service sector. Eur J Oper Res 279(2):620– 634
Jing L, Shen C, Yang L, Yu J, Ng MK (2017) Multi-label classification by semi-supervised singular value decomposition. IEEE Trans Image Process 26(10):4612–4625
Chen Z, Ren J (2021) Multi-label text classification with latent word-wise label information. Appl Intell 51(2):966–979
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Learning to Adapt to Unseen Abnormal Activities under Weak Supervision
Spatially Multi-conditional Image Generation
Font Generation with Missing Impression Labels
The Overlooked Classifier in Human-Object Interaction Recognition
A Similarity-based Framework for Classification Task
Self-paced learning to improve text row detection in historical documents with missing labels
Ordinal-Quadruplet: Retrieval of Missing Classes in Ordinal Time Series
Incomplete Multi-View Weak-Label Learning with Noisy Features and Imbalanced Labels
The Overlooked Classifier in Human-Object Interaction Recognition
Simple and Robust Loss Design for Multi-Label Learning with Missing Labels
Improving Predictions of Tail-end Labels using Concatenated BioMed-Transformers for Long Medical Documents
Multi-label Iterated Learning for Image Classification with Label Ambiguity
DeepXML: A Deep Extreme Multi-Label Learning Framework Applied to Short Text Documents
MetaMIML: Meta Multi-Instance Multi-Label Learning
Bootstrap Your Object Detector via Mixed Training
A Simple Approach to Image Tilt Correction with Self-Attention MobileNet for Smartphones
Multi-label Classification with Partial Annotations using Class-aware Selective Loss
Active Refinement for Multi-Label Learning: A Pseudo-Label Approach
Boost-RS: Boosted Embeddings for Recommender Systems and its Application to Enzyme-Substrate Interaction Prediction
Unbiased Loss Functions for Multilabel Classification with Missing Labels
AstronomicAL: An interactive dashboard for visualisation, integration and classification of data using Active Learning
Fast Multi-label Learning
SCIDA: Self-Correction Integrated Domain Adaptation from Single- to Multi-label Aerial Images
Statistical Dependency Guided Contrastive Learning for Multiple Labeling in Prenatal Ultrasound
An EM Framework for Online Incremental Learning of Semantic Segmentation
Multi-Label Gold Asymmetric Loss Correction with Single-Label Regulators
DECAF: Deep Extreme Classification with Label Features
T$_k$ML-AP: Adversarial Attacks to Top-$k$ Multi-Label Learning
ECLARE: Extreme Classification with Label Graph Correlations
XFL: Naming Functions in Binaries with Extreme Multi-label Learning
MLPD: Multi-Label Pedestrian Detector in Multispectral Domain
Multi-label Chaining with Imprecise Probabilities
Label-set Loss Functions for Partial Supervision: Application to Fetal Brain 3D MRI Parcellation
MuVAM: A Multi-View Attention-based Model for Medical Visual Question Answering
Recovering the Unbiased Scene Graphs from the Biased Ones
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.