---
title: "Out-of-the-Box vs. Fine-tuned: A New Benchmark for Military Automatic Target Detection and Recognition"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2608.17917v1"
permalink: "https://feed.astralor.com/items/itm_8110d1c5329d0adeb3d58528"
published: "2026-08-18T15:43:34.000Z"
score: 72
channel: "tech"
tags: ["DETR","VisDrone","YOLO","Military AI","Object Detection"]
---

# Out-of-the-Box vs. Fine-tuned: A New Benchmark for Military Automatic Target Detection and Recognition

## AI commentary

> This paper's value lies in pulling attention back to the plain truth that 'data and scenario decide everything'. For teams working on military vision or edge deployment, out-of-the-box performance and real gains from cross-domain fine-tuning are the most needed data points for budget allocation. Even if you are not in defense, the failure of small-object detection in A2G should alert anyone building drone-based vision systems.

## At a glance

This paper benchmarks six YOLO iterations and two DETR variants, both out-of-the-box and fine-tuned on VisDrone, for military Automatic Target Detection and Recognition (ATD/R). Using a newly acquired military-relevant dataset featuring vehicles, occlusions, and small targets, models are evaluated with mAP@0.5 and mAP@0.5:0.95 across Air-to-Ground (A2G) and Ground-to-Ground (G2G) perspectives, target size, and model size. Key findings: larger models outperform smaller ones, DETR-based models show promising results compared to YOLO, cross-domain fine-tuning improves A2G and small-object performance slightly, yet all models still struggle with small objects in A2G scenarios. The authors conclude that despite advances in object detection, in-domain training remains crucial for building capable ATD/R systems.

## Key points

- First systematic comparison of YOLO series and DETR variants under both out-of-the-box and fine-tuned settings on a new military dataset.
- Larger models generally outperform smaller ones, while DETR-based models show more promising accuracy than YOLO series.
- Cross-domain fine-tuning on VisDrone improves air-to-ground and small-object performance, albeit modestly.
- All models still struggle with small objects in air-to-ground scenarios, underscoring the importance of in-domain training.

## Full text

Automatic Target Detection and Recognition (ATD/R) is critical for military decision support and (semi-)autonomous operations. Recent advances in object detection and artificial intelligence (AI) significantly boosted the potential performance of ATD/R. However, the scarcity of publicly available military datasets limits the application of these systems. As a solution, this paper explores the use of publicly available models and civilian datasets to achieve reasonable performance in military contexts. We benchmark several state-of-the-art models, including six iterations of the YOLO series and two variations on the DETR framework, on a newly acquired military relevant dataset. This dataset features military vehicles and challenging circumstances, including various degrees of occlusions and small targets. The out-of-the-box version of each model is validated alongside a version finetuned on the VisDrone dataset. This dataset features small objects, an Air-to-Ground (A2G) perspective and relevant classes, potentially generalizing to our military ATD/R task. We compare the performance of the models using mAP@0.5 and mAP@0.5:0.95, across A2G and Ground-to-Ground (G2G) perspective, target size and model size, giving insight into the real-time capabilities of models. Our main findings are: (1) bigger models outperform smaller models, (2) DETR-based models show promising results compared to the YOLO series,(3) fine-tuning models on an out-of-domain A2G dataset, improves their A2G performance and slightly improves their performance on small objects, but (4) all models still struggle with detecting small objects in an A2G scenario. We conclude that, despite recent advances in object detection, in-domain training is still crucial for creating capable ATD/R systems.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_8110d1c5329d0adeb3d58528