跳到正文
arXiv cs.AI· Mousa Shaya·· 56 分钟前AI 评分41

SAR 车辆识别有多少来自车辆本身?MSTAR 与 ATRNet-STAR 上的背景捷径、俯角差距与部分样本库分析

How Much of SAR Vehicle Recognition Is the Vehicle? Background Shortcuts, Angle Gaps and Partial Libraries on MSTAR and ATRNet-STAR

AI 导读

一项 arXiv 研究用 ConvNeXt-Small 复现发现,SAR 车辆识别的近 99% 高分部分来自背景捷径:抹掉车辆中心 96x96 像素后,MSTAR 准确率仍达 73.3%,ATRNet-STAR 的 40 类 SOC 拆分仍达 63.3%。

正文 · 原文

View PDF HTML (experimental)

Abstract:Deep networks score near 99% on the MSTAR vehicle benchmark, and the newer ATRNet-STAR benchmark was built to be harder. We ask how much of these scores comes from the vehicle itself. With a modern network (ConvNeXt-Small, 3 seeds) we first reproduce the known MSTAR result: with the central 96x96 pixels zeroed out, accuracy is still 73.3% (chance 10%). The same shortcut is present in ATRNet-STAR, which was collected across several scenes: with the vehicle removed, accuracy is 63.3% on the 40-class SOC split (chance 2.5%). Under the official scene-change split, the background stops helping and starts hurting. Accuracy is 22.8% on full chips and 30.8% when only the vehicle is shown. A SAR foundation model, SARATR-X, leans on the background more than ConvNeXt does (+4 to +6 points with the vehicle removed, in every seed) and does not solve the scene change. We then hold the amount of training data fixed and vary the depression angles used for training. Accuracy is set mainly by the gap to the nearest training angle: 57% at 15 degrees, 39% at 30 degrees and 26% at 45 degrees. Adding more training angles does not help. Finally, when most classes have training images at the test angle and a few do not, the missing classes do worse than when no class has them: 9.0% instead of 22.4% at a 45-degree gap. Most of their images are assigned to known classes. We recommend reporting background-only and target-only controls, and the angle gap, next to any accuracy figure. Code is public.
Comments: 7 pages, 4 figures, 7 tables. Code: this https URL
Subjects: Artificial Intelligence (cs.AI)
Cite as: arXiv:2611.21827 [cs.AI]
  (or arXiv:2611.21827v1 [cs.AI] for this version)
  https://doi.org/10.48550/arXiv.2611.21827

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Mousa Shaya [view email]
[v1] Mon, 16 Nov 2026 19:43:55 UTC (205 KB)

来源:arXiv cs.AI · arxiv.org