mlsanityData to 14 Oct 2026

AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning

arXiv 1911.12423 ↗First posted 27 Nov 2019cs.CV cs.LGcited by 160

Not on the map. Why?

Abstract (arXiv)

Multi-task learning is an open and challenging problem in computer vision. The typical way of conducting multi-task learning with deep neural networks is either through handcrafted schemes that share all initial layers and branch out at an adhoc point, or through separate task-specific networks with an additional feature sharing/fusion mechanism. Unlike existing methods, we propose an adaptive sharing approach, called AdaShare, that decides what to share across which tasks to achieve the best recognition accuracy, while taking resource efficiency into account. Specifically, our main idea is to learn the sharing pattern through a task-specific policy that selectively chooses which layers to execute for a given task in the multi-task network. We efficiently optimize the task-specific policy jointly with the network weights, using standard back-propagation. Experiments on several challenging and diverse benchmark datasets with a variable number of tasks well demonstrate the efficacy of our approach over state-of-the-art methods. Project page: https://cs-people.bu.edu/sunxm/AdaShare/project.html.

Key facts. Cited by 160 papers in the map (data through 14 Oct 2026). First posted on arXiv 27 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 23; 2022: 34; 2023: 35; 2024: 37; 2025: 20; 2026: 11.

160 papers.

Sort:

By area:

  1. 2021Domain Generalization: A Surveycited by 764
  2. 2023Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspectivecited by 280
  3. 2024Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunitiescited by 254
  4. 2023AdaMerging: Adaptive Model Merging for Multi-Task Learningcited by 252
  5. 2021Efficiently Identifying Task Groupings for Multi-Task Learningcited by 222
  6. 2022Are Multimodal Transformers Robust to Missing Modality?cited by 186
  7. 2021DSelect-k: Differentiable Selection in the Mixture of Experts with Applications to Multi-Task Learningcited by 115
  8. 2023Multitask Prompt Tuning Enables Parameter-Efficient Transfer Learningcited by 115
  9. 2024Representation Surgery for Multi-Task Model Mergingcited by 96
  10. 2021RotoGrad: Gradient Homogenization in Multitask Learningcited by 83
  11. 2023Modular Deep Learningcited by 83
  12. 2023Sensitivity-Aware Visual Parameter-Efficient Fine-Tuningcited by 74
38 more
  1. 2022Auto-Lambda: Disentangling Dynamic Task Relationshipscited by 73
  2. 2024Distribution Matching for Multi-Task Learning of Classification Tasks: a Large-Scale Study on Faces & Beyondcited by 60
  3. 2021Model Zoo: A Growing "Brain" That Learns Continuallycited by 54
  4. 2024MetaGPT: Merging Large Language Models Using Model Exclusive Task Arithmeticcited by 53
  5. 2024A Survey on Model MoErging: Recycling and Routing Among Specialized Experts for Collaborative Learningcited by 52
  6. 2024LoRA Soups: Merging LoRAs for Practical Skill Composition Taskscited by 52
  7. 2022Task Adaptive Parameter Sharing for Multi-Task Learningcited by 42
  8. 2022A Survey of Multi-task Learning in Natural Language Processing: Regarding Task Relatedness and Training Methodscited by 42
  9. 2023FAME-ViL: Multi-Tasking Vision-Language Model for Heterogeneous Fashion Taskscited by 38
  10. 2021AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognitioncited by 36
  11. 2021Dynamic Network Quantization for Efficient Video Inferencecited by 36
  12. 2022Multi-Task Learning with Multi-Query Transformer for Dense Predictioncited by 34
  13. 2022GEMEL: Model Merging for Memory-Efficient, Real-Time Video Analytics at the Edgecited by 32
  14. 2022AdaTask: A Task-aware Adaptive Learning Rate Approach to Multi-task Learningcited by 31
  15. 2022Effective Adaptation in Multi-Task Co-Training for Unified Autonomous Drivingcited by 30
  16. 2023Prismer: A Vision-Language Model with Multi-Task Expertscited by 28
  17. 2022VALHALLA: Visual Hallucination for Machine Translationcited by 27
  18. 2021Task2Sim : Towards Effective Pre-training and Transfer from Synthetic Datacited by 26
  19. 2021Revisit Multimodal Meta-Learning through the Lens of Multi-Task Learningcited by 22
  20. 2022Controllable Dynamic Multi-Task Architecturescited by 21
  21. 2024E2E-MFD: Towards End-to-End Synchronous Multimodal Fusion Detectioncited by 21
  22. 2022Egocentric Video Task Translationcited by 19
  23. 2021AutoMTL: A Programming Framework for Automating Efficient Multi-Task Learningcited by 17
  24. 2022An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systemscited by 16
  25. 2021Variational Multi-Task Learning with Gumbel-Softmax Priorscited by 15
  26. 2022Mod-Squad: Designing Mixture of Experts As Modular Multi-Task Learnerscited by 15
  27. 2021Generative Modeling for Multi-task Visual Learningcited by 14
  28. 2022DiSparse: Disentangled Sparsification for Multitask Model Compressioncited by 14
  29. 2022PromptonomyViT: Multi-Task Prompt Learning Improves Video Transformers using Synthetic Scene Datacited by 14
  30. 2023Less is More: Selective Layer Finetuning with SubTuningcited by 14
  31. 2025Task Arithmetic in Trust Region: A Training-Free Model Merging Approach to Navigate Knowledge Conflictscited by 13
  32. 2024Exploring Training on Heterogeneous Data with Mixture of Low-rank Adapterscited by 12
  33. 2024SurgeryV2: Bridging the Gap Between Model Merging and Multi-Task Learning with Deep Representation Surgerycited by 12
  34. 2021Channel Exchanging Networks for Multimodal and Multitask Dense Image Predictioncited by 11
  35. 2022A Multi-modal Fusion Framework Based on Multi-task Correlation Learning for Cancer Prognosis Predictioncited by 11
  36. 2023MyoDex: A Generalizable Prior for Dexterous Manipulationcited by 11
  37. 2024GO4Align: Group Optimization for Multi-Task Alignmentcited by 11
  38. 2022Beyond RGB: Scene-Property Synthesis with Neural Radiance Fieldscited by 10

50 most cited of 160 All 160 (JSON)