Papers › Understanding Dark Scenes by Contrasting Multi-Modal Observations
Understanding Dark Scenes by Contrasting Multi-Modal Observations
Xiaoyu Dong, Naoto Yokoya
Understanding dark scenes based on multi-modal image data is challenging, as both the visible and auxiliary modalities provide limited semantic information for the task. Previous methods focus on fusing the two modalities but neglect the correlations among semantic classes when minimizing losses to align pixels with labels, resulting in inaccurate class predictions. To address these issues, we introduce a supervised multi-modal contrastive learning approach to increase the semantic discriminability of the learned multi-modal feature spaces by jointly performing cross-modal and intra-modal contrast under the supervision of the class correlations. The cross-modal contrast encourages same-class embeddings from across the two modalities to be closer and pushes different-class ones apart. The intra-modal contrast forces same-class or different-class embeddings within each modality to be together or apart. We validate our approach on a variety of tasks that cover diverse light conditions and image modalities. Experiments show that our approach can effectively enhance dark scene understanding based on multi-modal images with limited semantics by shaping semantic-discriminative feature spaces. Comparisons with previous methods demonstrate our state-of-the-art performance. Code and pretrained models are available at https://github.com/palmdong/SMMCL.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
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.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Semantic Segmentation | LLRGBD-synthetic | SMMCL (SegNeXt-B) | mIoU | 68.76 | #1 of 8 | Archive leaderboard | report |
| Semantic Segmentation | LLRGBD-synthetic | SMMCL (SegFormer-B2) | mIoU | 67.77 | #2 of 8 | Archive leaderboard | report |
| Semantic Segmentation | LLRGBD-synthetic | SMMCL (ResNet-101) | mIoU | 64.40 | #5 of 8 | Archive leaderboard | report |
| Semantic Segmentation | NYU Depth v2 | SMMCL (SegNeXt-B) | Mean IoU | 55.8% | #24 of 121 | Archive leaderboard | report |
| Semantic Segmentation | NYU Depth v2 | SMMCL (SegFormer-B2) | Mean IoU | 53.7% | #32 of 121 | Archive leaderboard | report |
| Semantic Segmentation | NYU Depth v2 | SMMCL (ResNet-101) | Mean IoU | 52.5% | #44 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.
Methods
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