mlsanityData to 7 Oct 2026

MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learning

arXiv 2001.06902 ↗First posted 19 Jan 2020cs.CVcited by 157

Not on the map. Why?

Abstract (arXiv)

In this paper, we argue about the importance of considering task interactions at multiple scales when distilling task information in a multi-task learning setup. In contrast to common belief, we show that tasks with high affinity at a certain scale are not guaranteed to retain this behaviour at other scales, and vice versa. We propose a novel architecture, namely MTI-Net, that builds upon this finding in three ways. First, it explicitly models task interactions at every scale via a multi-scale multi-modal distillation unit. Second, it propagates distilled task information from lower to higher scales via a feature propagation module. Third, it aggregates the refined task features from all scales via a feature aggregation unit to produce the final per-task predictions. Extensive experiments on two multi-task dense labeling datasets show that, unlike prior work, our multi-task model delivers on the full potential of multi-task learning, that is, smaller memory footprint, reduced number of calculations, and better performance w.r.t. single-task learning. The code is made publicly available: https://github.com/SimonVandenhende/Multi-Task-Learning-PyTorch.

Key facts. Cited by 157 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Jan 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 18; 2022: 28; 2023: 37; 2024: 32; 2025: 24; 2026: 18.

157 papers.

Sort:

By area:

  1. 2021Geometry Uncertainty Projection Network for Monocular 3D Object Detectioncited by 155
  2. 2022M3ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-designcited by 97
  3. 2022InvPT: Inverted Pyramid Multi-task Transformer for Dense Scene Understandingcited by 89
  4. 2021Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimationcited by 80
  5. 2022Auto-Lambda: Disentangling Dynamic Task Relationshipscited by 73
  6. 2021Exploring Relational Context for Multi-Task Dense Predictioncited by 71
  7. 2021InverseForm: A Loss Function for Structured Boundary-Aware Segmentationcited by 65
  8. 2023VMT-Adapter: Parameter-Efficient Transfer Learning for Multi-Task Dense Scene Understandingcited by 62
  9. 2024Multi-Task Dense Prediction via Mixture of Low-Rank Expertscited by 58
  10. 2021Fine-grained Semantics-aware Representation Enhancement for Self-supervised Monocular Depth Estimationcited by 55
  11. 2022Discovering Object Masks with Transformers for Unsupervised Semantic Segmentationcited by 54
  12. 2022Polyhistor: Parameter-Efficient Multi-Task Adaptation for Dense Vision Taskscited by 52
38 more
  1. 2023TaskExpert: Dynamically Assembling Multi-Task Representations with Memorial Mixture-of-Expertscited by 45
  2. 2024MTLoRA: A Low-Rank Adaptation Approach for Efficient Multi-Task Learningcited by 44
  3. 2021Learning Multiple Dense Prediction Tasks from Partially Annotated Datacited by 42
  4. 2022Multi-Task Learning with Multi-Query Transformer for Dense Predictioncited by 34
  5. 2021Learning to Relate Depth and Semantics for Unsupervised Domain Adaptationcited by 32
  6. 2022Efficient Multi-Task RGB-D Scene Analysis for Indoor Environmentscited by 32
  7. 2021Dual Transfer Learning for Event-based End-task Prediction via Pluggable Event to Image Translationcited by 31
  8. 2021Instance-wise Occlusion and Depth Orders in Natural Scenescited by 31
  9. 2023SA-BEV: Generating Semantic-Aware Bird's-Eye-View Feature for Multi-view 3D Object Detectioncited by 30
  10. 2022MGNet: Monocular Geometric Scene Understanding for Autonomous Drivingcited by 27
  11. 2023DeMT: Deformable Mixer Transformer for Multi-Task Learning of Dense Predictioncited by 27
  12. 2023Dual-Balancing for Multi-Task Learningcited by 27
  13. 2022DenseMTL: Cross-task Attention Mechanism for Dense Multi-task Learningcited by 25
  14. 2023Edge-MoE: Memory-Efficient Multi-Task Vision Transformer Architecture with Task-level Sparsity via Mixture-of-Expertscited by 23
  15. 2021Semi-supervised Multi-task Learning for Semantics and Depthcited by 22
  16. 2023InvPT++: Inverted Pyramid Multi-Task Transformer for Visual Scene Understandingcited by 22
  17. 2024MTMamba: Enhancing Multi-Task Dense Scene Understanding by Mamba-Based Decoderscited by 22
  18. 2023PanopticPartFormer++: A Unified and Decoupled View for Panoptic Part Segmentationcited by 19
  19. 2023Mitigating Task Interference in Multi-Task Learning via Explicit Task Routing with Non-Learnable Primitivescited by 18
  20. 2024DiffusionMTL: Learning Multi-Task Denoising Diffusion Model from Partially Annotated Datacited by 18
  21. 2024Spider: A Unified Framework for Context-dependent Concept Segmentationcited by 18
  22. 2023FedHCA2: Towards Hetero-Client Federated Multi-Task Learningcited by 17
  23. 2025Selective Task Group Updates for Multi-Task Optimizationcited by 15
  24. 2022PromptonomyViT: Multi-Task Prompt Learning Improves Video Transformers using Synthetic Scene Datacited by 14
  25. 2023Vision Transformer Adapters for Generalizable Multitask Learningcited by 14
  26. 2023Prompt Guided Transformer for Multi-Task Dense Predictioncited by 13
  27. 2024SwinMTL: A Shared Architecture for Simultaneous Depth Estimation and Semantic Segmentation from Monocular Camera Imagescited by 13
  28. 2024MICDrop: Masking Image and Depth Features via Complementary Dropout for Domain-Adaptive Semantic Segmentationcited by 13
  29. 2023TSP-Transformer: Task-Specific Prompts Boosted Transformer for Holistic Scene Understandingcited by 12
  30. 2023BridgeNet: Comprehensive and Effective Feature Interactions via Bridge Feature for Multi-task Dense Predictionscited by 12
  31. 2021Channel Exchanging Networks for Multimodal and Multitask Dense Image Predictioncited by 11
  32. 2024StainDiffuser: MultiTask Dual Diffusion Model for Virtual Stainingcited by 11
  33. 2024Quantifying Task Priority for Multi-Task Optimizationcited by 10
  34. 2024MTMamba++: Enhancing Multi-Task Dense Scene Understanding via Mamba-Based Decoderscited by 10
  35. 2021Spatio-Temporal Multi-Task Learning Transformer for Joint Moving Object Detection and Segmentationcited by 9
  36. 2023Performance-aware Approximation of Global Channel Pruning for Multitask CNNscited by 9
  37. 2023Transferring to Real-World Layouts: A Depth-aware Framework for Scene Adaptationcited by 9
  38. 2024A Backpack Full of Skills: Egocentric Video Understanding with Diverse Task Perspectivescited by 9

50 most cited of 157 All 157 (JSON)