Papers › Missing Modality Robustness in Semi-Supervised Multi-Modal Semantic Segmentation
Missing Modality Robustness in Semi-Supervised Multi-Modal Semantic Segmentation
Harsh Maheshwari, Yen-Cheng Liu, Zsolt Kira
Using multiple spatial modalities has been proven helpful in improving semantic segmentation performance. However, there are several real-world challenges that have yet to be addressed: (a) improving label efficiency and (b) enhancing robustness in realistic scenarios where modalities are missing at the test time. To address these challenges, we first propose a simple yet efficient multi-modal fusion mechanism Linear Fusion, that performs better than the state-of-the-art multi-modal models even with limited supervision. Second, we propose M3L: Multi-modal Teacher for Masked Modality Learning, a semi-supervised framework that not only improves the multi-modal performance but also makes the model robust to the realistic missing modality scenario using unlabeled data. We create the first benchmark for semi-supervised multi-modal semantic segmentation and also report the robustness to missing modalities. Our proposal shows an absolute improvement of up to 10% on robust mIoU above the most competitive baselines. Our code is available at https://github.com/harshm121/M3L
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):
get_citation_path(paper_1="2304.10756", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2304.10756")
Code
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.
A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
1 archive task tag without a task page not shown.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Semantic Segmentation | SUN-RGBD | DFormer-L | Mean IoU (test) | 48.17 | #44 of 44 | Archive leaderboard | report |
| Semantic Segmentation | Stanford2D3D - RGBD | Linear Fusion (Segformer B2) | mIoU | 57.16 | #4 of 6 | Archive leaderboard | report |
| Semi-Supervised Semantic Segmentation | 2D-3D-S | M3L (Linear Fusion B2) | mIoU (0.1% labels) | 40.05 | #1 of 1 | Archive leaderboard | report |
| Semi-Supervised Semantic Segmentation | 2D-3D-S | M3L (Linear Fusion B2) | mIoU (0.2% labels) | 44.62 | #1 of 1 | Archive leaderboard | report |
| Semi-Supervised Semantic Segmentation | 2D-3D-S | M3L (Linear Fusion B2) | mIoU (1% labels) | 49.28 | #1 of 1 | Archive leaderboard | report |
| Semi-Supervised Semantic Segmentation | Stanford 2D-3D | M3L (Linear Fusion - Segformer B2) | MM-Robust mIoU (0.1% labels) | 41.36 | #1 of 2 | Archive leaderboard | report |
| Semi-Supervised Semantic Segmentation | Stanford 2D-3D | M3L (Linear Fusion - Segformer B2) | mIoU (0.1% labels) | 44.1 | #1 of 2 | Archive leaderboard | report |
| Semi-Supervised Semantic Segmentation | Stanford 2D-3D | Mean Teacher (Linear Fusion - Segformer B2) | mIoU (0.1% labels) | 41.7 | #2 of 2 | 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
Introduced by this paper: M3L
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