# Training-Free Metrics for Synthetic Object Detection Data: A Proxy for Detector Performance

Source: [Training-Free Metrics for Synthetic Object Detection Data: A Proxy for Detector Performance](<https://www.sota2.com/research/paper/6a34cd3a206542251d7c6055>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-07-18T05:00:05.624Z

Authors: Myeongseok Nam, Donghun Yeo, Seungwook Kim

Published: 2026-06-18T05:46:23.000Z

## Abstract

Synthetic images are increasingly used to augment scarce real data for object detection. However, not all synthetic sets help equally, and the only way to know a set's value is to train a detector on it, which is slow and demands dense annotation. We ask whether a training-free metric can instead rank candidate synthetic training sets by their downstream utility. Existing image-set metrics such as FID, KID, and MMD compare two feature distributions with a single global statistic, which we show is mis-specified for detection-data selection in two ways: it is blind to per-image composition (object count, box scale, class mix), and even at fixed composition its global averaging washes out the appearance differences that separate high-mAP pools from low-mAP ones. We propose Conditional-Composition Domain Match (CCDM), which converts any feature-space distance into a composition-stratified comparison, matching candidate and target within metadata-defined strata without training a detector. On COCO and VisDrone-DET, the best CCDM variant ranks 19 candidate training sets in strong agreement with YOLOv8 mAP (Spearman \\r{ho} = 0.97 and 0.96), outperforming FID, KID, and MMD. Furthermore, CCDM holds when reference metadata comes from detector pseudo-labels rather than ground-truth boxes.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Object Detection on VisDrone-DET (test-dev)](<https://www.sota2.com/research/sota/object-detection-on-visdrone-det-test-dev.md>): Object Detection; VisDrone-DET (test-dev); mAP@.5:.95: 18.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2606.19817>)

[PDF](<https://arxiv.org/pdf/2606.19817.pdf>)