Multi-Label Classification

369 papers with code • 10 benchmarks • 28 datasets

Multi-Label Classification is the supervised learning problem where an instance may be associated with multiple labels. This is an extension of single-label classification (i.e., multi-class, or binary) where each instance is only associated with a single class label.

Source: Deep Learning for Multi-label Classification

Libraries

Use these libraries to find Multi-Label Classification models and implementations
3 papers
488
2 papers
15,282
2 papers
2,911
See all 11 libraries.

Toward Robustness in Multi-label Classification: A Data Augmentation Strategy against Imbalance and Noise

disl-lab/balancemix 12 Dec 2023

Multi-label classification poses challenges due to imbalanced and noisy labels in training data.

9
12 Dec 2023

Language-Guided Transformer for Federated Multi-Label Classification

jack24658735/fedlgt 12 Dec 2023

Nevertheless, it is still challenging for FL to deal with user heterogeneity in their local data distribution in the real-world FL scenario, and this issue becomes even more severe in multi-label image classification.

6
12 Dec 2023

Adaptive Hinge Balance Loss for Document-Level Relation Extraction

Jize-W/HingeABL EMNLP 2023

In this paper, we propose to downweight the easy negatives by utilizing a distance between the classification threshold and the predicted score of each relation.

5
06 Dec 2023

Long-tailed multi-label classification with noisy label of thoracic diseases from chest X-ray

laihaoran/ltml-mimic-cxr 29 Nov 2023

This work establishes a foundation for robust CAD methods, achieving a balance in identifying a spectrum of thoracic diseases in CXRs.

0
29 Nov 2023

Scalable Label Distribution Learning for Multi-Label Classification

ailearn-ml/sldl 28 Nov 2023

Most existing MLC methods are based on the assumption that the correlation of two labels in each label pair is symmetric, which is violated in many real-world scenarios.

0
28 Nov 2023

Category-Wise Fine-Tuning for Image Multi-label Classification with Partial Labels

maxium0526/category-wise-fine-tuning International Conference on Neural Information Processing 2023

A single model submitted to the competition server for the official evaluation achieves mAUC 91. 82% on the test set, which is the highest single model score in the leaderboard and literature.

4
27 Nov 2023

VALUED -- Vision and Logical Understanding Evaluation Dataset

espressovi/value-dataset 21 Nov 2023

In order to address this, we present the VALUE (Vision And Logical Understanding Evaluation) Dataset, consisting of 200, 000$+$ annotated images and an associated rule set, based on the popular board game - chess.

9
21 Nov 2023

ICXML: An In-Context Learning Framework for Zero-Shot Extreme Multi-Label Classification

yaxinzhuars/icxml 16 Nov 2023

This paper focuses on the task of Extreme Multi-Label Classification (XMC) whose goal is to predict multiple labels for each instance from an extremely large label space.

0
16 Nov 2023

Generalized test utilities for long-tail performance in extreme multi-label classification

mwydmuch/xcolumns NeurIPS 2023

As such, it is characterized by long-tail labels, i. e., most labels have very few positive instances.

0
09 Nov 2023

Exploring Best Practices for ECG Signal Processing in Machine Learning

imilas/ecg_augmentation 2 Nov 2023

In this work we apply down-sampling, normalization, and filtering functions to 3 different multi-label ECG datasets and measure their effects on 3 different high-performing time-series classifiers.

2
02 Nov 2023