# Do Generative Metrics Predict YOLO Performance? An Evaluation Across Models, Augmentation Ratios, and Dataset Complexity

arXiv: https://arxiv.org/abs/2602.18525 · HTML: https://mlsanity.com/paper/2602.18525/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 52 of its 78 references that are in the map.
- First posted on arXiv 20 Feb 2026.

## Builds on (most cited first, 30 of 52)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://mlsanity.com/paper/2207.02696/) (2022)
- [Improved Precision and Recall Metric for Assessing Generative Models](https://mlsanity.com/paper/1904.06991/) (2019)
- [Revisiting Unreasonable Effectiveness of Data in Deep Learning Era](https://mlsanity.com/paper/1707.02968/) (2017)
- [Reliable Fidelity and Diversity Metrics for Generative Models](https://mlsanity.com/paper/2002.09797/) (2020)
- [Assessing Generative Models via Precision and Recall](https://mlsanity.com/paper/1806.00035/) (2018)
- [The Effectiveness of Data Augmentation in Image Classification using Deep Learning](https://mlsanity.com/paper/1712.04621/) (2017)
- [End-to-End Semi-Supervised Object Detection with Soft Teacher](https://mlsanity.com/paper/2106.09018/) (2021)
- [Rethinking FID: Towards a Better Evaluation Metric for Image Generation](https://mlsanity.com/paper/2401.09603/) (2023)
- [Unbiased Teacher for Semi-Supervised Object Detection](https://mlsanity.com/paper/2102.09480/) (2021)
- [Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomization](https://mlsanity.com/paper/1804.06516/) (2018)
- [LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generation](https://mlsanity.com/paper/2303.17189/) (2023)
- [Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection](https://mlsanity.com/paper/1708.01642/) (2017)
- [Projected GANs Converge Faster](https://mlsanity.com/paper/2111.01007/) (2021)
- [Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models](https://mlsanity.com/paper/2306.04675/) (2023)
- [How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Models](https://mlsanity.com/paper/2102.08921/) (2021)

## Abstract (arXiv)

Synthetic images are increasingly used to augment object-detection training sets, but reliably evaluating a synthetic dataset before training remains difficult: standard global generative metrics (e.g., FID) often do not predict downstream detection mAP. We present a controlled evaluation of synthetic augmentation for YOLOv11 across three single-class detection regimes -- Traffic Signs (sparse/near-saturated), Cityscapes Pedestrian (dense/occlusion-heavy), and COCO PottedPlant (multi-instance/high-variability). We benchmark six GAN-, diffusion-, and hybrid-based generators over augmentation ratios from 10% to 150% of the real training split, and train YOLOv11 both from scratch and with COCO-pretrained initialization, evaluating on held-out real test splits (mAP@0.50:0.95). For each dataset-generator-augmentation configuration, we compute pre-training dataset metrics under a matched-size bootstrap protocol, including (i) global feature-space metrics in both Inception-v3 and DINOv2 embeddings and (ii) object-centric distribution distances over bounding-box statistics. Synthetic augmentation yields substantial gains in the more challenging regimes (up to +7.6% and +30.6% relative mAP in Pedestrian and PottedPlant, respectively) but is marginal in Traffic Signs and under pretrained fine-tuning. To separate metric signal from augmentation quantity, we report both raw and augmentation-controlled (residualized) correlations with multiple-testing correction, showing that metric-performance alignment is strongly regime-dependent and that many apparent raw associations weaken after controlling for augmentation level.