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

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

19 Jan 2020ECCV 2020 8arXiv:2001.06902archive 2025-07-28

Simon Vandenhende, Stamatios Georgoulis, Luc van Gool

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.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

SimonVandenhende/Multi-Task-Learning-PyTorch officialmentioned in papermentioned on GitHubpytorchNOASSERTIONSyntology: not harvested 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

Multi-Task LearningSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Segmentation NYU Depth v2 MTI-Net (HRNet-48) Mean IoU 49.0 #73 of 121 Archive leaderboard report
Semantic Segmentation UrbanLF MTINet (HRNetV2-W48) mIoU (Real) n.a. #7 of 14 Archive leaderboard report
Semantic Segmentation UrbanLF MTINet (HRNetV2-W48) mIoU (Syn) 79.10 #7 of 14 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.

Methods

1-bit AdamAdam

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