Research map / Architectures and efficiency / Attention and transformers
Pruning Parameterization With Bi-Level Optimization for Efficient Semantic Segmentation on the Edge
Changdi Yang, Pu Zhao, Yanyu Li, Wei Niu, Jiexiong Guan, Hao Tang, Minghai Qin, 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 |
|---|---|---|---|
| prune TopFormer layer widths using the proposed parameterization and bi-level optimization | TopFormer on ADE20K · ADE20K val | mIoU (%): 36.1 -> 37.5 | Improved |
| prune TopFormer layer widths using the proposed parameterization and bi-level optimization | TopFormer on Cityscapes · Cityscapes val | mIoU%: 70.6 -> 74.7 | Improved |
| use the proposed pruning method instead of TopFormer-S | TopFormer on PASCAL VOC 2012 · PASCAL VOC 2012 test | mIoU%: 69.8 -> 73.4 | Improved |
| prune DeepLabV3+ MobileNetV2 with the proposed method | DeepLabV3+ on Cityscapes · Cityscapes val | mIoU%: 69.0 -> 70.9 | Improved |
| add implicit gradients to the mask update (ablation) | the proposed pruning method · Cityscapes val | mIoU: 71.9 -> 73.6 | Improved |
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.
- CHEX — CHEX: CHannel EXploration for CNN Model Compression (CVPR 2022) · 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
- Dynamic Token Pruning in Plain Vision Transformers for Semantic Segmentation (ICCV 2023 · similarity 0.88)
- SAViT: Structure-Aware Vision Transformer Pruning via Collaborative Optimization (NeurIPS 2022 · similarity 0.87)
- Token Cropr: Faster ViTs for Quite a Few Tasks (CVPR 2025 · similarity 0.87)
- Zero-TPrune: Zero-Shot Token Pruning through Leveraging of the Attention Graph in Pre-Trained Transformers (CVPR 2024 · similarity 0.86)
- Collaborative Multi-Mode Pruning for Vision-Language Models (CVPR 2026 · similarity 0.85)
- Structural Pruning via Spatial-aware Information Redundancy for Semantic Segmentation (AAAI 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.
