AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

Efficient Joint-Dimensional Search with Solution Space Regularization for Real-Time Semantic Segmentation

Peng Ye, Baopu Li, Tao Chen, Jiayuan Fan, Zhen Mei, Lin Chen, Chongyan Zuo, Qinghua Chi, Wanli Ouyang

IJCV 2022 · Architectures and efficiency › Neural architecture search · approach: Latency-aware architecture search · 11 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 SSR loss (ablation)progressive shrinking search · Cityscapes val dilation searchmIoU (%): 66.95 -> 68.06Improved
add SSR loss to PDARTS (ablation)PDARTS · Cityscapes val dilation searchmIoU (%): 66.09 -> 66.36Improved
add SSR loss to SGAS (ablation)SGAS · Cityscapes val dilation searchmIoU (%): 66.59 -> 67.25Improved
use level-based progressive shrinking instead of SGAS-style (ablation)Ours without SSR · Cityscapes val dilation searchmIoU (%): 66.59 -> 66.95Improved
use SSR loss instead of L1 loss (ablation)progressive shrinking · Cityscapes val dilation searchmIoU (%): 65.47 -> 68.06Improved
use SSR loss instead of L2 loss (ablation)progressive shrinking · Cityscapes val dilation searchmIoU (%): 65.81 -> 68.06Improved
use our search scheme instead of DARTS (ablation)dilation search · Cityscapes valmIoU (%): 65.81 -> 68.06Improved
add channel, spatial and depth dimensions to dilation-only search under FLOPs constraint (ablation)joint search · Cityscapes val, 7.8G FLOPsmIoU (%): 64.63 -> 67.49Improved
add channel, spatial and depth dimensions to dilation-only search without FLOPs constraint (ablation)joint search · Cityscapes valmIoU (%): 68.04 -> 68.06No clear effect
add manual dilation arrangement to baseline1 (ablation)baseline1 · Cityscapes valmIoU (%): 59.38 -> 64.84Improved
add aggregation block in retraining (ablation)searched model · Cityscapes valmIoU (%): 68.70 -> 69.55Improved
add common training skills in retraining (ablation)searched model · Cityscapes valmIoU (%): 69.55 -> 73.67Improved

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