AI Paper Atlas

Research map / Detection and segmentation / CNN features

Cross-Image Pixel Contrasting for Semantic Segmentation

Tianfei Zhou, Wenguan Wang

TPAMI 2024 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 134 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 intra-image pixel contrast (ablation)HRNetV2-W48 · Cityscapes val (40K iters)mIoU: 78.1 -> 78.9Improved
add inter-image pixel contrast (ablation)HRNetV2-W48 · Cityscapes val (40K iters)mIoU: 78.1 -> 81.0Improved
add pixel memory to mini-batch contrast (ablation)HRNetV2-W48 · Cityscapes val (40K iters)mIoU: 79.8 -> 80.5Improved
add region memory to mini-batch contrast (ablation)HRNetV2-W48 · Cityscapes val (40K iters)mIoU: 79.8 -> 80.2Improved
use both pixel and region memory (ablation)HRNetV2-W48 · Cityscapes val (40K iters)mIoU: 80.5 -> 81.0Improved
use semi-hard instead of random pos/neg sampling (ablation)HRNetV2-W48 · Cityscapes val (40K iters)mIoU: 79.3 -> 80.1Improved
use segmentation-aware hard anchors instead of random (ablation)HRNetV2-W48 · Cityscapes val (40K iters)mIoU: 80.1 -> 81.0Improved
use semi-hard instead of hardest sampling (ablation)HRNetV2-W48 · Cityscapes val (40K iters)mIoU: 80.5 -> 81.0Improved
use contrastive loss instead of Lovasz loss (ablation)HRNetV2-W48 · Cityscapes val (40K iters)mIoU: 80.3 -> 81.0Improved
add AAF loss on top of contrastive loss (ablation)HRNetV2-W48 · Cityscapes val (40K iters)mIoU: 81.0 -> 81.0No clear effect
add Lovasz loss on top of contrastive loss (ablation)HRNetV2-W48 · Cityscapes val (40K iters)mIoU: 81.0 -> 81.5Improved
add pixel contrast to OCROCR (HRNetV2-W48) · Cityscapes test (train+val)mIoU: 82.4 -> 83.2Improved

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