mlsanityData to 14 Oct 2026

DenseMTL: Cross-task Attention Mechanism for Dense Multi-task Learning

arXiv 2206.08927 ↗First posted 17 Jun 2022cs.CV cs.AI cs.ROcited by 25

Not on the map. Why?

Abstract (arXiv)

Multi-task learning has recently emerged as a promising solution for a comprehensive understanding of complex scenes. In addition to being memory-efficient, multi-task models, when appropriately designed, can facilitate the exchange of complementary signals across tasks. In this work, we jointly address 2D semantic segmentation and three geometry-related tasks: dense depth estimation, surface normal estimation, and edge estimation, demonstrating their benefits on both indoor and outdoor datasets. We propose a novel multi-task learning architecture that leverages pairwise cross-task exchange through correlation-guided attention and self-attention to enhance the overall representation learning for all tasks. We conduct extensive experiments across three multi-task setups, showing the advantages of our approach compared to competitive baselines in both synthetic and real-world benchmarks. Additionally, we extend our method to the novel multi-task unsupervised domain adaptation setting. Our code is available at https://github.com/cv-rits/DenseMTL

Key facts. Cited by 25 papers in the map (data through 14 Oct 2026). Builds on 30 of its 42 references that are in the map. First posted on arXiv 17 Jun 2022.

Builds on

30 of 42 references.

References · 30

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  5. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  6. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  7. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  8. 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,423
  9. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,358
  10. 2018Dual Attention Network for Scene Segmentationcited by 1,003
  11. 2017GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networkscited by 834
  12. 2018Multi-Task Learning as Multi-Objective Optimizationcited by 821
18 more
  1. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 782
  2. 2018Taskonomy: Disentangling Task Transfer Learningcited by 634
  3. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
  4. 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 403
  5. 2019Which Tasks Should Be Learned Together in Multi-task Learning?cited by 375
  6. 2016Virtual Worlds as Proxy for Multi-Object Tracking Analysiscited by 341
  7. 2018PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsingcited by 224
  8. 2016UberNet: Training a `Universal' Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memorycited by 200
  9. 2020MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learningcited by 157
  10. 2019Pattern-Affinitive Propagation across Depth, Surface Normal and Semantic Segmentationcited by 142
  11. 2019DADA: Depth-aware Domain Adaptation in Semantic Segmentationcited by 97
  12. 2021Exploring Relational Context for Multi-Task Dense Predictioncited by 71
  13. 2020Three Ways to Improve Semantic Segmentation with Self-Supervised Depth Estimationcited by 66
  14. 2017Unsupervised Learning of Geometry with Edge-aware Depth-Normal Consistencycited by 40
  15. 2020Distilled Semantics for Comprehensive Scene Understanding from Videoscited by 39
  16. 2021Geometric Unsupervised Domain Adaptation for Semantic Segmentationcited by 33
  17. 2021Learning to Relate Depth and Semantics for Unsupervised Domain Adaptationcited by 32
  18. 2021Semi-supervised Multi-task Learning for Semantics and Depthcited by 22

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 7; 2024: 6; 2025: 5; 2026: 7.

25 papers.

Sort:

  1. 2023Material Palette: Extraction of Materials from a Single Imagecited by 28
  2. 2024InterACT: Inter-dependency Aware Action Chunking with Hierarchical Attention Transformers for Bimanual Manipulationcited by 22
  3. 2023Challenges for Monocular 6D Object Pose Estimation in Roboticscited by 21
  4. 2023Vision Transformer Adapters for Generalizable Multitask Learningcited by 14
  5. 2024SwinMTL: A Shared Architecture for Simultaneous Depth Estimation and Semantic Segmentation from Monocular Camera Imagescited by 13
  6. 2024MICDrop: Masking Image and Depth Features via Complementary Dropout for Domain-Adaptive Semantic Segmentationcited by 13
  7. 2023Cross-Task Attention Network: Improving Multi-Task Learning for Medical Imaging Applicationscited by 4
  8. 2025M2H: Multi-Task Learning with Efficient Window-Based Cross-Task Attention for Monocular Spatial Perceptioncited by 3
  9. 2023Open Challenges for Monocular Single-shot 6D Object Pose Estimationcited by 2
  10. 2023X-PDNet: Accurate Joint Plane Instance Segmentation and Monocular Depth Estimation with Cross-Task Distillation and Boundary Correctioncited by 2
  11. 2024Multi-Cohort Framework with Cohort-Aware Attention and Adversarial Mutual-Information Minimization for Whole Slide Image Classificationcited by 1
  12. 2024Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritizationcited by 1
13 more
  1. 2025Occlusion Boundary and Depth: Mutual Enhancement via Multi-Task Learningcited by 1
  2. 2026LASS-ODE: Scaling ODE Computations to Connect Foundation Models with Dynamical Physical Systemscited by 1
  3. 2023MetaMorphosis: Task-oriented Privacy Cognizant Feature Generation for Multi-task Learningcited by 0
  4. 2024AutoTask: Task Aware Multi-Faceted Single Model for Multi-Task Ads Relevancecited by 0
  5. 2025MT-CYP-Net: Multi-Task Network for Pixel-Level Crop Yield Prediction Under Very Few Samplescited by 0
  6. 2025A Survey on Deep Multi-Task Learning in Connected Autonomous Vehiclescited by 0
  7. 2025Efficient Domain-Adaptive Multi-Task Dense Prediction with Vision Foundation Modelscited by 0
  8. 2026Adaptive Bidirectional Task Interaction for Joint Segmentation and Classification of Breast Ultrasoundcited by 0
  9. 2026Efficient RGB-D Scene Understanding via Multi-task Adaptive Learning and Cross-dimensional Feature Guidancecited by 0
  10. 2026Semantic Aware Feature Extraction for Enhanced 3D Reconstructioncited by 0
  11. 2026PEML: Parameter-efficient Multi-Task Learning with Optimized Continuous Promptscited by 0
  12. 2026BTI-Net: Bidirectional Decoder-Level Task Interaction via Uncertainty-Aware Gating for Multi-Task Medical Image Analysiscited by 0
  13. 2026DPNeXt: A Lightweight Multi-Scale Feature Fusion Framework for Efficient ViT-Based Multi-Task Dense Predictioncited by 0