Research map / Detection and segmentation / CNN features
BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation
Changqian Yu, Jingbo Wang, Chao Peng, Changxin Gao, Gang Yu, Nong Sang
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 |
|---|---|---|---|
| replace standard U-shape-4s with U-shape-8s in the Context Path (ablation) | Context Path · Cityscapes val | mIoU: 60.79% to 66.01% | Improved |
| add Spatial Path (FFM fusion) (ablation) | Context Path (Xception39) · Cityscapes val | mIoU: 66.01 -> 67.42 | Improved |
| fuse paths with Feature Fusion Module instead of summation (ablation) | CP+SP · Cityscapes val | mIoU: 66.82 -> 67.42 | Improved |
| add global average pooling to Context Path (ablation) | CP+SP(FFM) · Cityscapes val | mIoU: 67.42% to 68.42% | Improved |
| add Attention Refinement Module (ablation) | CP+SP(FFM) · Cityscapes val | mIoU: 67.42 -> 68.72 | Improved |
| add both global pooling and ARM (ablation) | CP+SP(FFM) · Cityscapes val | mIoU: 67.42 -> 71.40 | Improved |
| use U-shape-4s instead of U-shape-8s (ablation) | U-shape-8s · Cityscapes val | mIoU: 66.01 -> 66.13 | No clear effect |
| swap Xception39 backbone for Res18 in FCN-32s (ablation) | FCN-32s · Cityscapes val | mIoU: 60.78 -> 61.58 | Mixed |
| swap Xception39 for Res18 in BiSeNet | BiSeNet · Cityscapes test | mIoU: 68.4 -> 74.7 | Improved |
| swap Res18 for Res101 in BiSeNet | BiSeNet · Cityscapes test | mIoU: 77.7 -> 78.9 | Improved |
| swap Res18 for Res101 in BiSeNet | BiSeNet · COCO-Stuff val | mIoU: 28.1 -> 31.3 | Improved |
Later papers that compared with this method
10 later accepted papers report BiSeNetV1 as a baseline in their results tables; 7 of them report a better number on most of the results they share with it.
- Golden Cudgel Network for Real-Time Semantic Segmentation (CVPR 2025 · better on 0 of 2 shared results)
- Labels4Free: Unsupervised Segmentation Using StyleGAN (ICCV 2021 · better on 1 of 1 shared result)
- Patch Proposal Network for Fast Semantic Segmentation of High-Resolution Images (AAAI 2020 · better on 1 of 2 shared results)
- FasterSeg: Searching for Faster Real-time Semantic Segmentation (ICLR 2020 · better on 1 of 1 shared result)
- Highly Efficient Salient Object Detection with 100K Parameters (ECCV 2020 · better on 1 of 1 shared result)
- Segmenting Transparent Objects in the Wild (ECCV 2020 · better on 1 of 1 shared result)
- DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation (CVPR 2019 · better on 0 of 2 shared results)
- SPGNet: Semantic Prediction Guidance for Scene Parsing (ICCV 2019 · better on 1 of 1 shared result)
2 more not listed.
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- SegNet — SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation (TPAMI 2017) · better on 2 of 2 shared results
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
- BiSeNet V2: Bilateral Network with Guided Aggregation for Real-Time Semantic Segmentation (IJCV 2021 · similarity 0.96)
- Rethinking BiSeNet for Real-Time Semantic Segmentation (CVPR 2021 · similarity 0.93)
- PIDNet: A Real-Time Semantic Segmentation Network Inspired by PID Controllers (CVPR 2023 · similarity 0.88)
- DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation (CVPR 2019 · similarity 0.87)
- FasterSeg: Searching for Faster Real-time Semantic Segmentation (ICLR 2020 · similarity 0.86)
- BFANet: Revisiting 3D Semantic Segmentation with Boundary Feature Analysis (CVPR 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.
