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

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

17 Jun 2022arXiv:2206.08927archive 2025-07-28

Ivan Lopes, Tuan-Hung Vu, Raoul de Charette

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

Paper PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

astra-vision/densemtl officialmentioned in papermentioned on GitHubpytorch report

cv-rits/densemtl officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

2D Semantic Segmentation Depth Estimation Domain Adaptation Multi-Task Learning Representation Learning Semantic Segmentation Surface Normal Estimation Unsupervised Domain Adaptation

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Semantic Segmentation	NYU Depth v2	DenseMTL	Mean IoU	40.84%	#109 of 121	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections