AI Paper Atlas

Research map / Detection and segmentation / CNN features

Tensor Low-Rank Reconstruction for Semantic Segmentation

Wanli Chen, Xinge Zhu, Ruoqi Sun, Junjun He, Ruiyu Li, Xiaoyong Shen, Bei Yu

ECCV 2020 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 83 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 TGM+TRM tensor low-rank reconstruction (ablation)ResNet-50 baseline · PASCAL VOC12 valmIoU (%): 68.7 -> 78.6Improved
add global pooling module (GPM) (ablation)ResNet-50 + TGM+TRM · PASCAL VOC12 valmIoU (%): 78.6 -> 79.2Improved
add auxiliary loss after Res-4 (ablation)ResNet-50 + TGM+TRM + GPM · PASCAL VOC12 valmIoU (%): 79.2 -> 79.8Improved
use ResNet-101 instead of ResNet-50 (ablation)RecoNet · PASCAL VOC12 valmIoU (%): 79.8 -> 81.4Improved
add multi-scale and flip testing (ablation)RecoNet ResNet-101 · PASCAL VOC12 valmIoU (%): 81.4 -> 82.1Improved
fine-tune on VOC12 original train set (ablation)RecoNet ResNet-101 · PASCAL VOC12 valmIoU (%): 82.1 -> 82.9Improved
increase tensor rank from 16 to 64 (ablation)RecoNet · PASCAL VOC12 valmIoU (%): 81.2 -> 82.1Improved
increase tensor rank from 64 to 128 (ablation)RecoNet · PASCAL VOC12 valmIoU (%): 82.1 -> 80.7Hurt
add TGM+TRM (ablation)ResNet-50 baseline (Cityscapes val) · Cityscapes valmIoU (%): 73.1 -> 78.9Improved
use RecoNet context module instead of EMANet (ablation)ResNet-101 (single scale) · PASCAL VOC12 valmIoU (%): 80.09 -> 81.40Improved
use RecoNet instead of DANet context moduleResNet-101 (single scale) · PASCAL VOC12 valmIoU (%): 79.64 -> 81.40Improved
use TGM+TRM instead of non-local blockcontext module cost · computational cost (512 channels)FLOPs: 19.33G -> 0.0215GImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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