AI Paper Atlas

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

CVPR 2023 · Architectures and efficiency › Attention and transformers · approach: Vision transformer pruning · 23 citations (OpenAlex)

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 changedWhereMeasuredEffect
prune TopFormer layer widths using the proposed parameterization and bi-level optimizationTopFormer on ADE20K · ADE20K valmIoU (%): 36.1 -> 37.5Improved
prune TopFormer layer widths using the proposed parameterization and bi-level optimizationTopFormer on Cityscapes · Cityscapes valmIoU%: 70.6 -> 74.7Improved
use the proposed pruning method instead of TopFormer-STopFormer on PASCAL VOC 2012 · PASCAL VOC 2012 testmIoU%: 69.8 -> 73.4Improved
prune DeepLabV3+ MobileNetV2 with the proposed methodDeepLabV3+ on Cityscapes · Cityscapes valmIoU%: 69.0 -> 70.9Improved
add implicit gradients to the mask update (ablation)the proposed pruning method · Cityscapes valmIoU: 71.9 -> 73.6Improved

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy