Papers › AsymFormer: Asymmetrical Cross-Modal Representation Learning for Mobile Platform...
AsymFormer: Asymmetrical Cross-Modal Representation Learning for Mobile Platform Real-Time RGB-D Semantic Segmentation
Siqi Du, Weixi Wang, Renzhong Guo, Ruisheng Wang, Yibin Tian, Shengjun Tang
Understanding indoor scenes is crucial for urban studies. Considering the dynamic nature of indoor environments, effective semantic segmentation requires both real-time operation and high accuracy.To address this, we propose AsymFormer, a novel network that improves real-time semantic segmentation accuracy using RGB-D multi-modal information without substantially increasing network complexity. AsymFormer uses an asymmetrical backbone for multimodal feature extraction, reducing redundant parameters by optimizing computational resource distribution. To fuse asymmetric multimodal features, a Local Attention-Guided Feature Selection (LAFS) module is used to selectively fuse features from different modalities by leveraging their dependencies. Subsequently, a Cross-Modal Attention-Guided Feature Correlation Embedding (CMA) module is introduced to further extract cross-modal representations. The AsymFormer demonstrates competitive results with 54.1% mIoU on NYUv2 and 49.1% mIoU on SUNRGBD. Notably, AsymFormer achieves an inference speed of 65 FPS (79 FPS after implementing mixed precision quantization) on RTX3090, demonstrating that AsymFormer can strike a balance between high accuracy and efficiency.
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 |
|---|---|---|---|---|---|---|---|
| Real-Time Semantic Segmentation | NYU Depth v2 | AsymFormer | Speed (FPS) | 65.5 (3090) | #1 of 10 | Archive leaderboard | report |
| Real-Time Semantic Segmentation | NYU Depth v2 | AsymFormer | Speed(ms/f) | 15.3 | #1 of 10 | Archive leaderboard | report |
| Real-Time Semantic Segmentation | NYU Depth v2 | AsymFormer | mIoU | 54.1 | #1 of 10 | Archive leaderboard | report |
| Semantic Segmentation | NYU Depth v2 | AsymFormer | Mean IoU | 55.3% | #27 of 121 | Archive leaderboard | report |
| Semantic Segmentation | SUN-RGBD | DFormer-B | Mean IoU | 49.1% | #25 of 44 | 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