AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Single-Temporal Supervised Learning for Universal Remote Sensing Change Detection

Zhuo Zheng, Yanfei Zhong, Ailong Ma, Liangpei Zhang

IJCV 2024 · Detection and segmentation › Open-set and few-shot detection · approach: Remote sensing segmentation and change · 26 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 single-temporal supervised learning with ChangeMixin (ChangeStar) over DPCCFarSeg · LEVIR-CD allF1: 71.0 -> 79.3Improved
add ChangeMixin2 and generalized STAR (ChangeStar2) over ChangeStarFarSeg R-50 · S2LookingF1: 21.2 -> 32.7Improved
add semantic supervision (ablation)ChangeStar baseline · LEVIR-CD allIoU: 61.9 -> 62.4Improved
add temporal symmetry (ablation)ChangeStar baseline · LEVIR-CD allF1: 76.4 -> 78.1Improved
add both semantic supervision and temporal symmetry (ablation)ChangeStar · LEVIR-CD allF1: 76.4 -> 79.3Improved
use xor instead of or label assignment (ablation)ChangeStar · LEVIR-CD allIoU: 43.8 -> 65.7Improved
add temporal difference network (ablation)ChangeStar R-18 · LEVIR-CD testF1: 77.4 -> 78.9Improved
add stochastic self-contrast (ablation)ChangeStar R-18 + TDN · LEVIR-CD testF1: 78.9 -> 81.2Improved
use stronger augmentation in stochastic self-contrast (ablation)ChangeStar2 · LEVIR-CD testF1: 81.2 -> 83.2Improved
reduce xView2 training data to 890 imagesChangeStar R-18 · LEVIR-CD testF1 gap: -12.8 -> -20.6Hurt
use larger backbone with less dataChangeStar RX-101 32x4d · LEVIR-CD testF1 gap: -9.7 -> -11.5Mixed
single-temporal ChangeStar2 vs bitemporal supervised ChangeStar2FarSeg · DynamicEarthNet val*SCS: 19.4 -> 20.2Improved

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