# Enhancing object detection robustness: A synthetic and natural perturbation approach

arXiv: https://arxiv.org/abs/2304.10622 · HTML: https://mlsanity.com/paper/2304.10622/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 39 references that are in the map.
- First posted on arXiv 20 Apr 2023.

## Builds on (most cited first, 22 of 22)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [Dynamic Routing Between Capsules](https://mlsanity.com/paper/1710.09829/) (2017)
- [Fast Online Object Tracking and Segmentation: A Unifying Approach](https://mlsanity.com/paper/1812.05050/) (2018)
- [Getting to Know Low-light Images with The Exclusively Dark Dataset](https://mlsanity.com/paper/1805.11227/) (2018)
- [Hypercolumns for Object Segmentation and Fine-grained Localization](https://mlsanity.com/paper/1411.5752/) (2014)
- [Understanding How Image Quality Affects Deep Neural Networks](https://mlsanity.com/paper/1604.04004/) (2016)
- [Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation](https://mlsanity.com/paper/1906.02611/) (2019)
- [Fusion of Detected Objects in Text for Visual Question Answering](https://mlsanity.com/paper/1908.05054/) (2019)
- [Why Do Better Loss Functions Lead to Less Transferable Features?](https://mlsanity.com/paper/2010.16402/) (2020)
- [RGBT Salient Object Detection: A Large-scale Dataset and Benchmark](https://mlsanity.com/paper/2007.03262/) (2020)
- [T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos](https://mlsanity.com/paper/1604.02532/) (2016)
- [Ablation Studies in Artificial Neural Networks](https://mlsanity.com/paper/1901.08644/) (2019)
- [Image Captioning and Visual Question Answering Based on Attributes and External Knowledge](https://mlsanity.com/paper/1603.02814/) (2016)
- [AugLy: Data Augmentations for Robustness](https://mlsanity.com/paper/2201.06494/) (2022)
- [On Classification of Distorted Images with Deep Convolutional Neural Networks](https://mlsanity.com/paper/1701.01924/) (2017)
- [An Effective Anti-Aliasing Approach for Residual Networks](https://mlsanity.com/paper/2011.10675/) (2020)
- [Using learned optimizers to make models robust to input noise](https://mlsanity.com/paper/1906.03367/) (2019)
- [Using Synthetic Corruptions to Measure Robustness to Natural Distribution Shifts](https://mlsanity.com/paper/2107.12052/) (2021)

## Built on by (most cited first, 3 of 3)

- [Non-Uniform Illumination Attack for Fooling Convolutional Neural Networks](https://mlsanity.com/paper/2409.03458/) (2024)
- [Enhancing Maritime Object Detection in Real-Time with RT-DETR and Data Augmentation](https://mlsanity.com/paper/2510.07346/) (2025)
- [Domain generalization and synthetic data in object detection: the enabler, the probe, and the gap](https://mlsanity.com/paper/2610.00030/) (2026)

## Abstract (arXiv)

Robustness against real-world distribution shifts is crucial for the successful deployment of object detection models in practical applications. In this paper, we address the problem of assessing and enhancing the robustness of object detection models against natural perturbations, such as varying lighting conditions, blur, and brightness. We analyze four state-of-the-art deep neural network models, Detr-ResNet-101, Detr-ResNet-50, YOLOv4, and YOLOv4-tiny, using the COCO 2017 dataset and ExDark dataset. By simulating synthetic perturbations with the AugLy package, we systematically explore the optimal level of synthetic perturbation required to improve the models robustness through data augmentation techniques. Our comprehensive ablation study meticulously evaluates the impact of synthetic perturbations on object detection models performance against real-world distribution shifts, establishing a tangible connection between synthetic augmentation and real-world robustness. Our findings not only substantiate the effectiveness of synthetic perturbations in improving model robustness, but also provide valuable insights for researchers and practitioners in developing more robust and reliable object detection models tailored for real-world applications.