AI Paper Atlas

Research map / Detection and segmentation / CNN features

Lightweight and Progressively-Scalable Networks for Semantic Segmentation

Yiheng Zhang, Ting Yao, Zhaofan Qiu, Tao Mei

IJCV 2023 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 32 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
use 3x3 Conv instead of 3x3 SepConv as the block (ablation)multi-path network · Cityscapes valmIoU (%): 53.9 -> 66.2Improved
use 3x3 Conv instead of Inverted Residual block (ablation)multi-path network · Cityscapes valmIoU (%): 59.2 -> 66.2Improved
use 3x3 Conv instead of Bottleneck block (ablation)multi-path network · Cityscapes valmIoU (%): 55.7 -> 66.2Improved
use 3x3 Conv instead of Residual block (ablation)multi-path network · Cityscapes vallatency (ms): 5.24 -> 5.08Improved
add Bilateral-B bilinear path interaction (ablation)multi-path network · Cityscapes valmIoU (%): 66.9 -> 69.9Improved
use Bilateral-B instead of Bilateral-A interaction (ablation)multi-path network · Cityscapes vallatency (ms): 6.48 -> 5.97Improved
use Direct-A interaction instead of Bilateral-B (ablation)multi-path network · Cityscapes valmIoU (%): 69.9 -> 67.9Hurt
add depth expansion (step 1) to tiny networkLPS-Net tiny network · Cityscapes valmIoU (%): 24.1 -> 41.4Improved
expand width in steps 2 and 3LPS-Net · Cityscapes valmIoU (%): 41.4 -> 57.8Improved
expand resolution to two paths with 1/4 second path (step 6)LPS-Net · Cityscapes valmIoU (%): 62.3 -> 64.6Improved
scale from LPS-Net-S to LPS-Net-M by raising main resolution to 1LPS-Net · Cityscapes valmIoU (%): 66.1 -> 69.5Improved
adopt LPS-Net-S instead of FasterSegBDD100K segmentation · BDD100K valmIoU (%): 55.1 -> 55.9Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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