AI Paper Atlas

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

ATRNet-STAR: A Large Dataset and Benchmark Toward Remote Sensing Object Recognition in the Wild

Yongxiang Liu, Weijie Li, Li Liu, Jie Zhou, Bowen Peng, Yafei Song, Xuying Xiong, Wei Yang, Tianpeng Liu, Zhen Liu, Xiang Li

TPAMI 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Remote sensing segmentation and change · 44 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
train on simple scenes, test on complex scenes (SOC-40 to EOC-Scene)ConvNeXt · ATRNet-STAR classificationoverall accuracy (%): 96.0 -> 16.5Hurt
train on 15 degree depression, test on other angles (SOC-40 to EOC-Depression)ConvNeXt · ATRNet-STAR classificationoverall accuracy (%): 96.0 -> 43.1Hurt
train on azimuth 0-60 degrees, test on others (SOC-40 to EOC-Azimuth)SARATR-X · ATRNet-STAR classificationoverall accuracy (%): 96.4 -> 26.4Hurt
use complex-image methods instead of magnitude methods for scene shiftHDANet / LDSF / MS-CVNet · EOC-Scene classificationoverall accuracy (%): 16.5 -> 29.7 (LDSF); 33.6 (HDANet)Improved
use complex-image methods under band and polarization shiftMS-CVNet / LDSF · EOC-Band, EOC-Polarization classificationoverall accuracy (%): 89.2 -> 60.9 (LDSF) on EOC-Band; 84.6 -> 55.1 on EOC-PolarizationHurt
add self-supervised SAR pre-training (SARATR-X vs HiViT)HiViT · SOC-40 classificationoverall accuracy (%): 86.8 -> 96.4Improved
use two-stage detector instead of single-stage under EOCFaster RCNN / DiffDet4SAR / SARATR-X · ATRNet-STAR detectionmAP50: EOC-Scene 21.5 (YOLOv10) -> 37.2 (DiffDet4SAR)Improved
single-stage CenterNet under depression and polarization shiftCenterNet · EOC-Depression, EOC-Polarization detectionmAP50: 22.3 (YOLOv10) -> 33.5 EOC-Depression; 59.2 -> 74.8 EOC-PolarizationImproved
reduce training set size on logarithmic scaleclassification models · SOC-50accuracyHurt
pre-train on ATRNet-STAR SOC-40 before 5-shot fine-tuningclassification models · vehicle and aircraft SAR datasets (5-shot)accuracyImproved
pre-train on ATRNet-STAR before 5-shot fine-tuning on ship dataclassification models · ship SAR dataset (5-shot)accuracyNo clear effect

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