AI Paper Atlas

Research map / Detection and segmentation / CNN features

Not All Pixels are Equal: Learning Pixel Hardness for Semantic Segmentation

Xin Xiao, Daiguo Zhou, Jiagao Hu, Yi Hu, Yongchao Xu

IJCV 2025 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 8 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 hardness level learning (HL)UPerNet ResNet-18 · Cityscapes valmIoU: 74.39 -> 76.10Improved
add HLBiSeNetV2 · Cityscapes valmIoU: 72.92 -> 75.27Improved
add HLUPerNet ConvNeXt-Base · Cityscapes valmIoU: 80.89 -> 81.33Improved
add HLPSPNet ResNet-18 · iSAID valmIoU: 60.76 -> 62.93Improved
add HLDeepLabV3+ ResNet-101 · ADE20K valmIoU: 45.12 -> 45.43Improved
add HLFCN HRNet-W18 (small) · Total-Text testfgIoU: 66.62 -> 68.56Improved
add HL to U2PLU2PL (w/CutMix) · Cityscapes semi-supervised 1/16mIoU: 71.11 -> 72.62Improved
add HLDeepLabV3+ ResNet-101 · GTAV to CityscapesmIoU: 36.56 -> 43.06Improved
use HL pixel weights instead of cross-entropy (ablation)PSPNet ResNet-18 · Cityscapes valmIoU: 74.30 -> 75.60Improved
use focal loss pixel weights instead of cross-entropy (ablation)PSPNet ResNet-18 · Cityscapes valmIoU: 74.30 -> 73.35Hurt
use balanced CE instead of cross-entropy (ablation)PSPNet ResNet-101 · Cityscapes valmIoU: 79.60 -> 79.16Hurt
use OHEM CE instead of cross-entropy (ablation)PSPNet ResNet-101 · Cityscapes valmIoU: 79.60 -> 79.64No clear effect

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