AI Paper Atlas

Research map / Detection and segmentation / CNN features

Distributed Semantic Segmentation with Efficient Joint Source and Task Decoding

Danish Nazir, Timo Bartels, Jan Piewek, Thorsten Bagdonat, Tim Fingscheidt

ECCV 2024 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 2 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
replace separate source decoder and task decoder with a single joint source and task decoderdistributed DeepLabv3 ResNet-50 cloud DNN · COCO-2017 val#params (M): 16.78 -> 1.66Improved
replace separate source decoder and task decoder with joint decoderdistributed DeepLabv3 ResNet-50 cloud DNN · Cityscapes val#params (M): 42.44 -> 4.92Improved
joint decoding versus Ahuja et al. on rate-distortion mIoU, COCOdistributed semantic segmentation · COCO-2017 valmIoUImproved
joint decoding versus Ahuja et al. on rate-distortion mIoU, Cityscapesdistributed semantic segmentation · Cityscapes valmIoUNo clear effect
add training-time over-parameterization in the ASPP block of the joint decoder (ablation)joint decoder JD · COCO-2017 val and Cityscapes valmIoU at high bitratesImproved
increase ASPP feature maps F from 256 to 512 (ablation)joint decoder JD · COCO-2017 valmIoUMixed
use F=512 instead of 128 or 256 (ablation)joint decoder JD · Cityscapes valmIoUImproved
increase over-parameterization repetitions K from 1 to 2 (ablation)joint decoder JD · COCO-2017 valmIoUNo clear effect
use K=3 over-parameterization repetitions (ablation)joint decoder JD · Cityscapes valmIoUImproved

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