AI Paper Atlas

Research map / Detection and segmentation / CNN features

ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation

Sachin Mehta, Mohammad Rastegari, Anat Caspi, Linda Shapiro, Hannaneh Hajishirzi

ECCV 2018 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 1,048 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 PReLU instead of ReLU (ablation)ESPNet-A · Cityscapes valmIoU: 0.36 -> 0.38Improved
add residual skip-connections in ESP modules (ablation)ESPNet-A · Cityscapes valmIoU: 0.37 -> 0.39Improved
use strided ESP instead of strided convolution for downsampling (ablation)ESPNet-A · Cityscapes valmIoU: 0.38 -> 0.39Improved
raise width divider K from 2 to 8 (ablation)ESPNet-A · Cityscapes valmIoU: 0.415 -> 0.303Hurt
concatenate feature maps for width expansion (ESPNet-B) (ablation)ESPNet-A · Cityscapes valmIoU: 0.39 -> 0.40Improved
add input reinforcement (ESPNet-C) (ablation)ESPNet-B · Cityscapes valmIoU: 0.40 -> 0.42Improved
replace input reinforcement with input-aware fusion (ablation)ESPNet-C · Cityscapes valmIoU: 0.42 -> 0.42No clear effect
add light-weight decoder to ESPNet-C (ablation)ESPNet-C (alpha3=3) · Cityscapes valmIoU (%): 49.0 -> 56.3Improved
use point-wise reduce instead of 3x3 standard convolution (ablation)ESP module · Cityscapes valmIoU (%): 50.8 -> 49.0Hurt
use dilated convolutions instead of standard 3x3 in spatial pyramid (ablation)ESP module · Cityscapes valmIoU (%): 47.4 -> 49.0Improved
increase depth multiplier alpha3 from 3 to 8 (ablation)ESPNet · Cityscapes valmIoU (%): 56.3 -> 61.4Improved
use ESP module instead of MobileNet module in ESPNet-CESPNet-C · Cityscapes valmIoU: 7% higherImproved

Later papers that compared with this method

3 later accepted papers report ESPNetv2 as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

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