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.

miscellaneous-10

Multi-Task Learning

3260 papers • 126 benchmarks • 313 datasets

Multi-task learning aims to learn multiple different tasks simultaneously while maximizing performance on one or all of the tasks. ( Image credit: Cross-stitch Networks for Multi-task Learning )

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in multi-task-learning-20

Trend

Dataset

Best Model

Actions

Cityscapes test

Cityscapes test

OMNIGLOT

OMNIGLOT

CelebA

CelebA

Libraries

i

Use these libraries to find multi-task-learning-20 models and implementations

HSE-asavchenko/face-emotion-recogni…

4 papers 471

Datasets

Cityscapes

CelebA

NYUv2

Clotho

ETHICS

KP20k

Subtasks

Multi-task Language Understanding

Most implemented papers

RetinaFace: Single-stage Dense Face Localisation in the Wild

Jiankang Deng, J. Guo, S. Zafeiriou, I. Kotsia, Jinke Yu•Wed May 01 2019

A robust single-stage face detector, named RetinaFace, which performs pixel-wise face localisation on various scales of faces by taking advantages of joint extra-supervised and self-super supervised multi-task learning.

692

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

wireframe dataset

wireframe dataset

NYUv2

NYUv2

QM9

QM9

tomas-gajarsky/facetorch

4 papers 327

TartanAir

TartanAir

CELEX

Aff-Wild2

0

Language Models are Few-Shot Learners

I. Sutskever, Tom B. Brown, Alec Radford, Christopher Berner, Christopher Hesse, Scott Gray, Dario Amodei, A. Ramesh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Jack Clark, Gretchen Krueger, T. Henighan, Benjamin Mann, Sam McCandlish, Prafulla Dhariwal, Jeff Wu, Daniel M. Ziegler, Arvind Neelakantan, Mark Chen, Nick Ryder, Clemens Winter, Ariel Herbert-Voss, Melanie Subbiah, J. Kaplan, Pranav Shyam, R. Child, Eric Sigler, Ma-teusz Litwin, Benjamin Chess•Wed May 27 2020

GPT-3 achieves strong performance on many NLP datasets, including translation, question-answering, and cloze tasks, as well as several tasks that require on-the-fly reasoning or domain adaptation, such as unscrambling words, using a novel word in a sentence, or performing 3-digit arithmetic.

53675 0

FairMOT: On the Fairness of Detection and Re-identification in Multiple Object Tracking

Xinggang Wang, Wenyu Liu, Yifu Zhang, Chunyu Wang, Wenjun Zeng•Fri Apr 03 2020

This work presents a simple yet effective approach termed as FairMOT based on the anchor-free object detection architecture CenterNet, which outperforms the state-of-the-art methods by a large margin on several public datasets.

1568 0

Multi-task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics

Y. Gal, Alex Kendall, R. Cipolla•Thu May 18 2017

A principled approach to multi-task deep learning is proposed which weighs multiple loss functions by considering the homoscedastic uncertainty of each task, allowing us to simultaneously learn various quantities with different units or scales in both classification and regression settings.

3546 0

COVID-CT-Dataset: A CT Scan Dataset about COVID-19

Xuehai He, Pengtao Xie, Xingyi Yang, Jinyu Zhao, Yichen Zhang•Sun Mar 29 2020

An open-sourced dataset, which contains 349 COVID-19 CT images from 216 patients and 463 non-COVID- 19 CTs, is built, which is used to develop diagnosis methods based on multi-task learning and self-supervised learning that achieve an F1 of 0.90, an AUC of0.98, and an accuracy of 1.89.

898 0

Towards Real-Time Multi-Object Tracking

Shengjin Wang, Liang Zheng, Zhongdao Wang, Yixuan Liu•Thu Sep 26 2019

This work incorporates the appearance embedding model into a single-shot detector, such that the model can simultaneously output detections and the corresponding embeddings, and is formulated as a multi-task learning problem.

1038 0

Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts

Lichan Hong, Ed H. Chi, Jiaqi W. Ma, Zhe Zhao, Xinyang Yi, Jilin Chen•Wed Jul 18 2018

This work proposes a novel multi-task learning approach, Multi-gate Mixture-of-Experts (MMoE), which explicitly learns to model task relationships from data and demonstrates the performance improvements by MMoE on real tasks including a binary classification benchmark, and a large-scale content recommendation system at Google.

1435 0

Gradient Surgery for Multi-Task Learning

Chelsea Finn, S. Levine, Abhishek Gupta, Tianhe Yu, Saurabh Kumar, Karol Hausman•Sat Jan 18 2020

This work identifies a set of three conditions of the multi-task optimization landscape that cause detrimental gradient interference, and develops a simple yet general approach for avoiding such interference between task gradients.

1479 0

Measuring Massive Multitask Language Understanding

D. Song, Dan Hendrycks, Mantas Mazeika, Steven Basart, J. Steinhardt, Collin Burns, Andy Zou•Sun Sep 06 2020

While most recent models have near random-chance accuracy, the very largest GPT-3 model improves over random chance by almost 20 percentage points on average, however, on every one of the 57 tasks, the best models still need substantial improvements before they can reach expert-level accuracy.

6811 0

Adding a benchmark result helps the community track progress.

Multi-Task Learning | State-of-the-Art