Research map / Architectures and efficiency / Attention and transformers
Towards Real-Time Segmentation on the Edge
Yanyu Li, Changdi Yang, Pu Zhao, Geng Yuan, Wei Niu, Jiexiong Guan, Hao Tang, Minghai Qin, Qing Jin, Bin Ren, Xue Lin, Yanzhi Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add the lightweight inverted residual block to BiSeNetV2 (ablation) | BiSeNetV2 · Cityscapes | mIoU: 73.4 to 74.0 | Improved |
| Add the multi-head self-attention block to BiSeNetV2 (ablation) | BiSeNetV2 · Cityscapes | mIoU: 73.4 to 73.8 | Improved |
| Add auxiliary losses and self-distillation during search (ablation) | RTSeg · Cityscapes | mIoU: 74.5 to 75.3 | Improved |
| Use the latency-driven proxyless search process | RTSeg · Cityscapes | GPU days: 0.7 GPU days; Auto-DeepLab 3; FasterSeg 2; Fast-NAS 8; SparseMask 4.2; DCNAS 5.6 | Improved |
| Use RTSeg-M instead of BiSeNetV2 | Cityscapes · Cityscapes test | mIoU: 72.6 to 73.8 | Improved |
| Use RTSeg-L instead of DeepLabV3+ | ADE20K · ADE20K val | mIoU: 38.1 to 38.7 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- DCNAS — DCNAS: Densely Connected Neural Architecture Search for Semantic Image Segmentation (CVPR 2021) · better on 0 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Low-Latency Video Semantic Segmentation (CVPR 2018 · similarity 0.88)
- In Defense of Pre-Trained ImageNet Architectures for Real-Time Semantic Segmentation of Road-Driving Images (CVPR 2019 · similarity 0.86)
- Lightweight and Progressively-Scalable Networks for Semantic Segmentation (IJCV 2023 · similarity 0.86)
- DenseASPP for Semantic Segmentation in Street Scenes (CVPR 2018 · similarity 0.86)
- Pruning Parameterization With Bi-Level Optimization for Efficient Semantic Segmentation on the Edge (CVPR 2023 · similarity 0.86)
- RMP-SAM: Towards Real-Time Multi-Purpose Segment Anything (ICLR 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
