AI Paper Atlas

Research map / Detection and segmentation / CNN features

Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

Liang-Chieh Chen, Yukun Zhu, George Papandreou, Florian Schroff, Hartwig Adam

ECCV 2018 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 21,095 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 the proposed decoder (ablation)DeepLabv3 ResNet-101 OS16 · PASCAL VOC 2012 valmIOU (%): 77.21% -> 78.85%Improved
add the proposed decoder (ablation)DeepLabv3 ResNet-101 eval OS8 · PASCAL VOC 2012 valmIOU (%): 78.51% -> 79.35%Improved
reduce low-level channels to 48 with 1x1 conv vs 8 (ablation)decoder · PASCAL VOC 2012 valmIOU (%): 77.61% -> 78.21%Improved
use two 3x3 convs instead of one in decoder (ablation)decoder · PASCAL VOC 2012 valmIOU (%): 78.21% -> 78.85%Improved
use three 3x3 convs instead of two (ablation)decoder · PASCAL VOC 2012 valmIOU (%): 78.85% -> 78.02%Hurt
add Conv3 features to decoder (U-Net style) (ablation)decoder · PASCAL VOC 2012 valmIOU (%): 78.21% -> 78.61%No clear effect
train with output stride 32 instead of 16 (ablation)DeepLabv3+ ResNet-101 · PASCAL VOC 2012 valmIOU (%): 78.85% -> 77.37%Hurt
replace ResNet-101 with modified Xception (ablation)DeepLabv3 OS16/16 · PASCAL VOC 2012 valmIOU (%): 77.21% -> 79.17%Improved
add decoder (ablation)DeepLabv3 Xception OS16/16 · PASCAL VOC 2012 valmIOU (%): 79.17% -> 79.93%Improved
use depthwise separable conv in ASPP and decoder (ablation)DeepLabv3+ Xception · PASCAL VOC 2012 valMultiply-Adds: 89.76B -> 54.17BNo clear effect
pretrain on COCO (ablation)DeepLabv3+ Xception SC · PASCAL VOC 2012 valmIOU (%): 79.79% -> 82.20%Improved
pretrain on JFT additionally (ablation)DeepLabv3+ Xception SC COCO · PASCAL VOC 2012 valmIOU (%): 82.20% -> 83.03%Improved

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