mlsanityData to 13 Oct 2026

Many Task Learning with Task Routing

arXiv 1903.12117 ↗First posted 28 Mar 2019cs.CVcited by 50

Not on the map. Why?

Abstract (arXiv)

Typical multi-task learning (MTL) methods rely on architectural adjustments and a large trainable parameter set to jointly optimize over several tasks. However, when the number of tasks increases so do the complexity of the architectural adjustments and resource requirements. In this paper, we introduce a method which applies a conditional feature-wise transformation over the convolutional activations that enables a model to successfully perform a large number of tasks. To distinguish from regular MTL, we introduce Many Task Learning (MaTL) as a special case of MTL where more than 20 tasks are performed by a single model. Our method dubbed Task Routing (TR) is encapsulated in a layer we call the Task Routing Layer (TRL), which applied in an MaTL scenario successfully fits hundreds of classification tasks in one model. We evaluate our method on 5 datasets against strong baselines and state-of-the-art approaches.

Key facts. Cited by 50 papers in the map (data through 13 Oct 2026). First posted on arXiv 28 Mar 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 10; 2022: 11; 2023: 13; 2024: 8; 2025: 5; 2026: 3.

50 papers.

Sort:

By area:

  1. 2021UniT: Multimodal Multitask Learning with a Unified Transformercited by 195
  2. 2024InstructIR: High-Quality Image Restoration Following Human Instructionscited by 139
  3. 2023Modular Deep Learningcited by 83
  4. 2024Towards Modular LLMs by Building and Reusing a Library of LoRAscited by 72
  5. 2024Distribution Matching for Multi-Task Learning of Classification Tasks: a Large-Scale Study on Faces & Beyondcited by 60
  6. 2022Uni-Perceiver-MoE: Learning Sparse Generalist Models with Conditional MoEscited by 58
  7. 2022MulT: An End-to-End Multitask Learning Transformercited by 47
  8. 2022One Model is All You Need: Multi-Task Learning Enables Simultaneous Histology Image Segmentation and Classificationcited by 38
  9. 2024Multimodal Instruction Tuning with Conditional Mixture of LoRAcited by 36
  10. 2022Multi-Task Learning with Multi-Query Transformer for Dense Predictioncited by 34
  11. 2021INTERN: A New Learning Paradigm Towards General Visioncited by 33
  12. 2023Denoising Task Routing for Diffusion Modelscited by 28
38 more
  1. 2022Towards Versatile Embodied Navigationcited by 26
  2. 2022Universal Representations: A Unified Look at Multiple Task and Domain Learningcited by 23
  3. 2023Scalarization for Multi-Task and Multi-Domain Learning at Scalecited by 19
  4. 2023Mitigating Task Interference in Multi-Task Learning via Explicit Task Routing with Non-Learnable Primitivescited by 18
  5. 2024MT2ST: Adaptive Multi-Task to Single-Task Learningcited by 16
  6. 2021Variational Multi-Task Learning with Gumbel-Softmax Priorscited by 15
  7. 2021Towards a Unified Foundation Model: Jointly Pre-Training Transformers on Unpaired Images and Textcited by 14
  8. 2024Supervised Fine-tuning in turn Improves Visual Foundation Modelscited by 13
  9. 2023Same Same, But Different: Conditional Multi-Task Learning for Demographic-Specific Toxicity Detectioncited by 10
  10. 2023Multi-task Learning with 3D-Aware Regularizationcited by 8
  11. 2023Episodic Multi-Task Learning with Heterogeneous Neural Processescited by 8
  12. 2023MINOTAUR: Multi-task Video Grounding From Multimodal Queriescited by 6
  13. 2021Instance-Level Task Parameters: A Robust Multi-task Weighting Frameworkcited by 4
  14. 2021Improved optimization strategies for deep Multi-Task Networkscited by 4
  15. 2022Learning More May Not Be Better: Knowledge Transferability in Vision and Language Taskscited by 3
  16. 2023Provable Pathways: Learning Multiple Tasks over Multiple Pathscited by 3
  17. 2025Grounding Degradations in Natural Language for All-In-One Video Restorationcited by 3
  18. 2025Revisit the Imbalance Optimization in Multi-task Learning: An Experimental Analysiscited by 3
  19. 2022Learning Multi-Tasks with Inconsistent Labels by using Auxiliary Big Taskcited by 2
  20. 2023Multi-Task Structural Learning using Local Task Similarity induced Neuron Creation and Removalcited by 2
  21. 2024Deep Feature Surgery: Towards Accurate and Efficient Multi-Exit Networkscited by 2
  22. 2024Stylistic Multi-Task Analysis of Ukiyo-e Woodblock Printscited by 2
  23. 20253D-Aware Multi-Task Learning with Cross-View Correlations for Dense Scene Understandingcited by 2
  24. 2021RoutingGAN: Routing Age Progression and Regression with Disentangled Learningcited by 1
  25. 2021Plot2API: Recommending Graphic API from Plot via Semantic Parsing Guided Neural Networkcited by 1
  26. 2021Image interpretation by iterative bottom-up top-down processingcited by 1
  27. 2021Deep Safe Multi-Task Learningcited by 1
  28. 2022Curbing Task Interference using Representation Similarity-Guided Multi-Task Feature Sharingcited by 1
  29. 2022Highly Scalable Task Grouping for Deep Multi-Task Learning in Prediction of Epigenetic Eventscited by 1
  30. 2023Dense Multitask Learning to Reconfigure Comicscited by 1
  31. 2025Simplifying Multi-Task Architectures Through Task-Specific Normalizationcited by 1
  32. 2026Context Channel Capacity: An Information-Theoretic Framework for Understanding Catastrophic Forgettingcited by 1
  33. 2022Association Graph Learning for Multi-Task Classification with Category Shiftscited by 0
  34. 2023Task adaption by biologically inspired stochastic comodulationcited by 0
  35. 2023ATE-SG: Alternate Through the Epochs Stochastic Gradient for Multi-Task Neural Networkscited by 0
  36. 2025Parameter Aware Mamba Model for Multi-task Dense Predictioncited by 0
  37. 2026Cascaded Transfer: Learning Many Tasks under Budget Constraintscited by 0
  38. 2026Parameter-efficient Quantum Multi-task Learningcited by 0