AI Paper Atlas

Research map / Detection and segmentation / CNN features

Boosting Semantic Segmentation from the Perspective of Explicit Class Embeddings

Yuhe Liu, Chuanjian Liu, Kai Han, Quan Tang, Zengchang Qin

ICCV 2023 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 10 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
add Feature Reconstruction module (without diversity loss) (ablation)ECENet · ADE20K valmIoU (ss): 52.5 -> 53.1Improved
add diversity loss L_div to Feature Reconstruction (ablation)ECENet · ADE20K valmIoU (ss): 53.1 -> 53.4Improved
use gated update instead of plus update for class embeddings (ablation)Class Updater · ADE20K valmIoU (ss): 52.7 -> 53.4Improved
set diversity loss coefficient to 0.2 rather than 0.1 or 0.5 (ablation)Diversity loss · ADE20K valmIoU (ss): 53.25 / 53.40 / 52.65 for 0.1 / 0.2 / 0.5Mixed
apply gated updating to SegViT's randomly initialized class embeddingsSegViT (ViT-Base) · ADE20K valmIoU (ss): 51.3 -> 51.9Improved
replace SenFormer with ECENet on same SwinT-Large backboneSenFormer · ADE20K valmIoU (ms): 54.2 -> 55.2Improved
replace SenFormer with ECENet on same SwinT-Large backboneSenFormer · PASCAL-Context valmIoU (ms): 64.5 -> 65.9Improved
replace Mask2Former with ECENet on CityscapesMask2Former · Cityscapes valmIoU (ms): 84.3 -> 84.5Improved

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