Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

medical-8

Multi-Label Classification

3260 papers • 126 benchmarks • 313 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

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in multi-label-classification-32

Trend

Dataset

Best Model

Actions

MS-COCO

MS-COCO

PASCAL VOC 2007

PASCAL VOC 2007

CheXpert

CheXpert

Libraries

i

Use these libraries to find multi-label-classification-32 models and implementations

3 papers 487

Datasets

CheXpert

NUS-WIDE

ChestX-ray14

MIMIC-CXR

PASCAL VOC 2007

PASCAL VOC 2007

ECHR

Subtasks

Missing Labels Extreme Multi-Label Classification Medical Code Prediction Hierarchical Multi-label Classification

Most implemented papers

Densely Connected Convolutional Networks

Kilian Q. Weinberger, Zhuang Liu, Gao Huang•Wed Aug 24 2016

The Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward fashion, and has several compelling advantages: they alleviate the vanishing-gradient problem, strengthen feature propagation, encourage feature reuse, and substantially reduce the number of parameters.

41544

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

NUS-WIDE

NUS-WIDE

OpenImages-v6

OpenImages-v6

PASCAL VOC 2012

PASCAL VOC 2012

MLRSNet

MLRSNet

MRNet

MRNet

MIMIC-CXR

MIMIC-CXR

ChestX-ray14

ChestX-ray14

2 papers 15,236

Deci-AI/super-gradients

2 papers 4,255

2 papers 2,910

alibaba-damo-academy/FunASR

2 papers 2,768

benedekrozemberczki/karateclub

2 papers 2,066

yoshitomo-matsubara/torchdistill

2 papers 1,231

andreasveit/densenet-pytorch

2 papers 445

hycis/TensorGraph

2 papers 68

mwydmuch/napkinXC

2 papers 58

lab-midas/med_segmentation

2 papers 16

ECHR

Friedman1

MRNet

VizWiz-Classification

VizWiz-Classification

0

Learning to diagnose from scratch by exploiting dependencies among labels

L. Yao, Kevin Lyman, Eric Poblenz, Dmitry Dagunts, Ben Covington, D. Bernard•Fri Oct 27 2017

A partial solution to constraints in using LSTMs to leverage interdependencies among target labels in predicting 14 pathologic patterns from chest x-rays is presented and state of the art results on the largest publicly availablechest x-ray dataset from the NIH without pre-training are established.

359 0

node2vec: Scalable Feature Learning for Networks

J. Leskovec, Aditya Grover•Sat Jul 02 2016

In node2vec, an algorithmic framework for learning continuous feature representations for nodes in networks, a flexible notion of a node's network neighborhood is defined and a biased random walk procedure is designed, which efficiently explores diverse neighborhoods.

11814 0

From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification

André F. T. Martins, Ramón Fernández Astudillo•Thu Feb 04 2016

Sparsemax, a new activation function similar to the traditional softmax, but able to output sparse probabilities, is proposed, and an unexpected connection between this new loss and the Huber classification loss is revealed.

809 0

Multi-Task Learning as Multi-Objective Optimization

Ozan Sener, V. Koltun•Tue Oct 09 2018

This paper proposes an upper bound for the multi-objective loss and shows that it can be optimized efficiently, and proves that optimizing this upper bound yields a Pareto optimal solution under realistic assumptions.

1567 0

Asymmetric Loss For Multi-Label Classification

Lihi Zelnik-Manor, M. Protter, Emanuel Ben Baruch, T. Ridnik, Nadav Zamir, Asaf Noy, Itamar Friedman•Mon Sep 28 2020

This paper introduces a novel asymmetric loss ("ASL"), which enables to dynamically down-weights and hard-thresholds easy negative samples, while also discarding possibly mislabeled samples and demonstrating ASL applicability for other tasks, such as single-label classification and object detection.

723 0

SKEP: Sentiment Knowledge Enhanced Pre-training for Sentiment Analysis

Bolei He, Xinyan Xiao, Hua Wu, Haifeng Wang, Hao Tian, Can Gao, Hao Liu, Feng Wu•Mon May 11 2020

Sentiment Knowledge Enhanced Pre-training (SKEP) is introduced in order to learn a unified sentiment representation for multiple sentiment analysis tasks, and significantly outperforms strong pre-training baseline, and achieves new state-of-the-art results on most of the test datasets.

270 0

SCDV : Sparse Composite Document Vectors using soft clustering over distributional representations

Vivek Gupta, Dheeraj Mekala, Bhargavi Paranjape, H. Karnick•Mon Dec 19 2016

Through extensive experiments on multi-class and multi-label classification tasks, this work outperforms the previous state-of-the-art method, NTSG and achieves a significant reduction in training and prediction times compared to other representation methods.

49 0

ML-Net: multi-label classification of biomedical texts with deep neural networks

Zhiyong Lu, Yifan Peng, Jingcheng Du, Qingyu Chen, Yang Xiang, Cui Tao•Mon Nov 12 2018

OBJECTIVE In multi-label text classification, each textual document is assigned 1 or more labels. As an important task that has broad applications in biomedicine, a number of different computational methods have been proposed. Many of these methods, however, have only modest accuracy or efficiency and limited success in practical use. We propose ML-Net, a novel end-to-end deep learning framework, for multi-label classification of biomedical texts. MATERIALS AND METHODS ML-Net combines a label prediction network with an automated label count prediction mechanism to provide an optimal set of labels. This is accomplished by leveraging both the predicted confidence score of each label and the deep contextual information (modeled by ELMo) in the target document. We evaluate ML-Net on 3 independent corpora in 2 text genres: biomedical literature and clinical notes. For evaluation, we use example-based measures, such as precision, recall, and the F measure. We also compare ML-Net with several competitive machine learning and deep learning baseline models. RESULTS Our benchmarking results show that ML-Net compares favorably to state-of-the-art methods in multi-label classification of biomedical text. ML-Net is also shown to be robust when evaluated on different text genres in biomedicine. CONCLUSION ML-Net is able to accuractely represent biomedical document context and dynamically estimate the label count in a more systematic and accurate manner. Unlike traditional machine learning methods, ML-Net does not require human effort for feature engineering and is a highly efficient and scalable approach to tasks with a large set of labels, so there is no need to build individual classifiers for each separate label.

146 0

Extremely Randomized CNets for Multi-label Classification

T. Basile, Nicola Di Mauro, F. Esposito•Mon Nov 19 2018

The recently introduced Extremely Randomized CNets (XCNets) reduce the structure learning complexity making able to learn ensembles of XCNets outperforming state-of-the-art density estimators.

0 0

Adding a benchmark result helps the community track progress.

Multi-Label Classification | State-of-the-Art