mlsanityData to 7 Oct 2026

A Tree-Structured Multi-Task Model Recommender

arXiv 2203.05092 ↗First posted 10 Mar 2022cs.LG cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Tree-structured multi-task architectures have been employed to jointly tackle multiple vision tasks in the context of multi-task learning (MTL). The major challenge is to determine where to branch out for each task given a backbone model to optimize for both task accuracy and computation efficiency. To address the challenge, this paper proposes a recommender that, given a set of tasks and a convolutional neural network-based backbone model, automatically suggests tree-structured multi-task architectures that could achieve a high task performance while meeting a user-specified computation budget without performing model training. Extensive evaluations on popular MTL benchmarks show that the recommended architectures could achieve competitive task accuracy and computation efficiency compared with state-of-the-art MTL methods. Our tree-structured multi-task model recommender is open-sourced and available at https://github.com/zhanglijun95/TreeMTL.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 28 of its 55 references that are in the map. First posted on arXiv 10 Mar 2022.

Builds on

28 of 55 references.

References · 28

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  3. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  4. 2018Multi-Task Learning as Multi-Objective Optimizationcited by 809
  5. 2017An Overview of Multi-Task Learning in Deep Neural Networkscited by 791
  6. 2018Taskonomy: Disentangling Task Transfer Learningcited by 631
  7. 2018End-to-End Multi-Task Learning with Attentioncited by 533
  8. 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
  9. 2018FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Searchcited by 480
  10. 2016Cross-stitch Networks for Multi-task Learningcited by 466
  11. 2019Which Tasks Should Be Learned Together in Multi-task Learning?cited by 367
  12. 2018SNAS: Stochastic Neural Architecture Searchcited by 288
16 more
  1. 2014The Loss Surfaces of Multilayer Networkscited by 278
  2. 2019AdaShare: Learning What To Share For Efficient Deep Multi-Task Learningcited by 159
  3. 2019Attentive Single-Tasking of Multiple Taskscited by 148
  4. 2018NDDR-CNN: Layerwise Feature Fusing in Multi-Task CNNs by Neural Discriminative Dimensionality Reductioncited by 127
  5. 2020Learning to Branch for Multi-Task Learningcited by 114
  6. 2016Fully-adaptive Feature Sharing in Multi-Task Networks with Applications in Person Attribute Classificationcited by 93
  7. 2019Branched Multi-Task Networks: Deciding What Layers To Sharecited by 76
  8. 2020The Global Landscape of Neural Networks: An Overviewcited by 57
  9. 2018Real-Time Joint Semantic Segmentation and Depth Estimation Using Asymmetric Annotationscited by 51
  10. 2020Automated Search for Resource-Efficient Branched Multi-Task Networkscited by 51
  11. 2020MTL-NAS: Task-Agnostic Neural Architecture Search towards General-Purpose Multi-Task Learningcited by 50
  12. 2019Regularizing Deep Multi-Task Networks using Orthogonal Gradientscited by 36
  13. 2020Dynamic Task Weighting Methods for Multi-task Networks in Autonomous Driving Systemscited by 34
  14. 2020Multi-Task Learning for Dense Prediction Tasks: A Surveycited by 28
  15. 2019Deep Elastic Networks with Model Selection for Multi-Task Learningcited by 20
  16. 2021FBNetV5: Neural Architecture Search for Multiple Tasks in One Runcited by 15

Built on by

Cited by year

Citing papers per year: 2023: 4; 2024: 2.

6 papers.

  1. 2023STG-MTL: Scalable Task Grouping for Multi-Task Learning Using Data Mapcited by 3
  2. 2024Towards Principled Task Grouping for Multi-Task Learningcited by 3
  3. 2023Multi-Task Structural Learning using Local Task Similarity induced Neuron Creation and Removalcited by 2
  4. 2024AdapMTL: Adaptive Pruning Framework for Multitask Learning Modelcited by 2
  5. 2023Attacking All Tasks at Once Using Adversarial Examples in Multi-Task Learningcited by 1
  6. 2023Parameter-efficient Multi-Task and Multi-Domain Learning using Factorized Tensor Networkscited by 1