mlsanityData to 7 Oct 2026

Attentive Single-Tasking of Multiple Tasks

arXiv 1904.08918 ↗First posted 18 Apr 2019cs.CVcited by 148

Not on the map. Why?

Abstract (arXiv)

In this work we address task interference in universal networks by considering that a network is trained on multiple tasks, but performs one task at a time, an approach we refer to as "single-tasking multiple tasks". The network thus modifies its behaviour through task-dependent feature adaptation, or task attention. This gives the network the ability to accentuate the features that are adapted to a task, while shunning irrelevant ones. We further reduce task interference by forcing the task gradients to be statistically indistinguishable through adversarial training, ensuring that the common backbone architecture serving all tasks is not dominated by any of the task-specific gradients. Results in three multi-task dense labelling problems consistently show: (i) a large reduction in the number of parameters while preserving, or even improving performance and (ii) a smooth trade-off between computation and multi-task accuracy. We provide our system's code and pre-trained models at http://vision.ee.ethz.ch/~kmaninis/astmt/.

Key facts. Cited by 148 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 23; 2022: 21; 2023: 38; 2024: 34; 2025: 22; 2026: 10.

148 papers.

Sort:

By area:

  1. 2021Conflict-Averse Gradient Descent for Multi-task Learningcited by 441
  2. 2022Omnivore: A Single Model for Many Visual Modalitiescited by 214
  3. 2022Multi-Task Learning as a Bargaining Gamecited by 209
  4. 2024Twin-Merging: Dynamic Integration of Modular Expertise in Model Mergingcited by 114
  5. 2021Reasonable Effectiveness of Random Weighting: A Litmus Test for Multi-Task Learningcited by 100
  6. 2022InvPT: Inverted Pyramid Multi-task Transformer for Dense Scene Understandingcited by 89
  7. 2023Deep Model Fusion: A Surveycited by 89
  8. 2021RotoGrad: Gradient Homogenization in Multitask Learningcited by 82
  9. 2022Auto-Lambda: Disentangling Dynamic Task Relationshipscited by 73
  10. 2021Exploring Relational Context for Multi-Task Dense Predictioncited by 71
  11. 2023Independent Component Alignment for Multi-Task Learningcited by 69
  12. 2021InverseForm: A Loss Function for Structured Boundary-Aware Segmentationcited by 65
38 more
  1. 2022Factorizing Knowledge in Neural Networkscited by 59
  2. 2021PolyViT: Co-training Vision Transformers on Images, Videos and Audiocited by 58
  3. 2024Multi-Task Dense Prediction via Mixture of Low-Rank Expertscited by 58
  4. 2021Improving Speech Translation by Understanding and Learning from the Auxiliary Text Translation Taskcited by 54
  5. 2023Recon: Reducing Conflicting Gradients from the Root for Multi-Task Learningcited by 50
  6. 2024Smooth Tchebycheff Scalarization for Multi-Objective Optimizationcited by 50
  7. 2023TaskExpert: Dynamically Assembling Multi-Task Representations with Memorial Mixture-of-Expertscited by 45
  8. 2024MoME: Mixture of Multimodal Experts for Generalist Multimodal Large Language Modelscited by 45
  9. 2024MTLoRA: A Low-Rank Adaptation Approach for Efficient Multi-Task Learningcited by 44
  10. 2024DINO-Foresight: Looking into the Future with DINOcited by 44
  11. 2024Multimodal Instruction Tuning with Conditional Mixture of LoRAcited by 36
  12. 2021INTERN: A New Learning Paradigm Towards General Visioncited by 33
  13. 2023Direction-oriented Multi-objective Learning: Simple and Provable Stochastic Algorithmscited by 33
  14. 2021Learning to Relate Depth and Semantics for Unsupervised Domain Adaptationcited by 32
  15. 2021Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimationcited by 30
  16. 2022Improving Multi-Task Generalization via Regularizing Spurious Correlationcited by 28
  17. 2023ForkMerge: Mitigating Negative Transfer in Auxiliary-Task Learningcited by 28
  18. 2023Denoising Task Routing for Diffusion Modelscited by 28
  19. 2023Dual-Balancing for Multi-Task Learningcited by 27
  20. 2021Avoiding Catastrophe: Active Dendrites Enable Multi-Task Learning in Dynamic Environmentscited by 24
  21. 2021Semi-supervised Multi-task Learning for Semantics and Depthcited by 22
  22. 2021Revisit Multimodal Meta-Learning through the Lens of Multi-Task Learningcited by 22
  23. 2023InvPT++: Inverted Pyramid Multi-Task Transformer for Visual Scene Understandingcited by 22
  24. 2024MTMamba: Enhancing Multi-Task Dense Scene Understanding by Mamba-Based Decoderscited by 22
  25. 2023Mitigating Task Interference in Multi-Task Learning via Explicit Task Routing with Non-Learnable Primitivescited by 18
  26. 2024DiffusionMTL: Learning Multi-Task Denoising Diffusion Model from Partially Annotated Datacited by 18
  27. 2021AutoMTL: A Programming Framework for Automating Efficient Multi-Task Learningcited by 17
  28. 2023FedHCA2: Towards Hetero-Client Federated Multi-Task Learningcited by 17
  29. 2022Beyond Losses Reweighting: Empowering Multi-Task Learning via the Generalization Perspectivecited by 15
  30. 2022Mod-Squad: Designing Mixture of Experts As Modular Multi-Task Learnerscited by 15
  31. 2025Selective Task Group Updates for Multi-Task Optimizationcited by 15
  32. 2021ClimateGAN: Raising Climate Change Awareness by Generating Images of Floodscited by 14
  33. 2022Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Stochastic Approachcited by 14
  34. 2023Mirror U-Net: Marrying Multimodal Fission with Multi-task Learning for Semantic Segmentation in Medical Imagingcited by 14
  35. 2022Unsupervised RGB-to-Thermal Domain Adaptation via Multi-Domain Attention Networkcited by 13
  36. 2023Prompt Guided Transformer for Multi-Task Dense Predictioncited by 13
  37. 2023Auxiliary Learning as an Asymmetric Bargaining Gamecited by 12
  38. 2023TSP-Transformer: Task-Specific Prompts Boosted Transformer for Holistic Scene Understandingcited by 12

50 most cited of 148 All 148 (JSON)