Enhancing object detection robustness: A synthetic and natural
perturbation approach
- URL: http://arxiv.org/abs/2304.10622v1
- Date: Thu, 20 Apr 2023 19:55:51 GMT
- Title: Enhancing object detection robustness: A synthetic and natural
perturbation approach
- Authors: Nilantha Premakumara, Brian Jalaian, Niranjan Suri and Hooman Samani
- Abstract summary: Robustness against real-world distribution shifts is crucial for the successful deployment of object detection models in practical applications.
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.
Our comprehensive ablation study meticulously evaluates the impact of synthetic perturbations on object detection models performance against real-world distribution shifts.
- Score: 2.5337932872891202
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: 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.
Related papers
- Towards Evaluating the Robustness of Visual State Space Models [63.14954591606638]
Vision State Space Models (VSSMs) have demonstrated remarkable performance in visual perception tasks.
However, their robustness under natural and adversarial perturbations remains a critical concern.
We present a comprehensive evaluation of VSSMs' robustness under various perturbation scenarios.
arXiv Detail & Related papers (2024-06-13T17:59:44Z) - Precision and Adaptability of YOLOv5 and YOLOv8 in Dynamic Robotic Environments [0.0]
This study provides a comparative analysis of YOLOv5 and YOLOv8 models.
Contrary to initial expectations, YOLOv5 models demonstrated comparable, and in some cases superior, precision in object detection tasks.
arXiv Detail & Related papers (2024-06-01T06:17:43Z) - Best Practices and Lessons Learned on Synthetic Data for Language Models [83.63271573197026]
The success of AI models relies on the availability of large, diverse, and high-quality datasets.
Synthetic data has emerged as a promising solution by generating artificial data that mimics real-world patterns.
arXiv Detail & Related papers (2024-04-11T06:34:17Z) - Data Quality Aware Approaches for Addressing Model Drift of Semantic
Segmentation Models [1.6385815610837167]
This study investigates two prominent quality aware strategies to combat model drift.
The former leverages image quality assessment metrics to meticulously select high-quality training data, improving the model robustness.
The latter makes use of learned vectors feature from existing models to guide the selection of future data, aligning it with the model's prior knowledge.
arXiv Detail & Related papers (2024-02-11T18:01:52Z) - Derm-T2IM: Harnessing Synthetic Skin Lesion Data via Stable Diffusion
Models for Enhanced Skin Disease Classification using ViT and CNN [1.0499611180329804]
We aim to incorporate enhanced data transformation techniques by extending the recent success of few-shot learning.
We investigate the impact of incorporating newly generated synthetic data into the training pipeline of state-of-art machine learning models.
arXiv Detail & Related papers (2024-01-10T13:46:03Z) - Reliability in Semantic Segmentation: Can We Use Synthetic Data? [52.5766244206855]
This paper challenges cutting-edge generative models to automatically synthesize data for assessing reliability in semantic segmentation.
By fine-tuning Stable Diffusion, we perform zero-shot generation of synthetic data in OOD domains or inpainted with OOD objects.
We demonstrate a high correlation between the performance on synthetic data and the performance on real OOD data, showing the validity approach.
arXiv Detail & Related papers (2023-12-14T18:56:07Z) - End-to-End Learning of Hybrid Inverse Dynamics Models for Precise and
Compliant Impedance Control [16.88250694156719]
We present a novel hybrid model formulation that enables us to identify fully physically consistent inertial parameters of a rigid body dynamics model.
We compare our approach against state-of-the-art inverse dynamics models on a 7 degree of freedom manipulator.
arXiv Detail & Related papers (2022-05-27T07:39:28Z) - Non-Singular Adversarial Robustness of Neural Networks [58.731070632586594]
Adrial robustness has become an emerging challenge for neural network owing to its over-sensitivity to small input perturbations.
We formalize the notion of non-singular adversarial robustness for neural networks through the lens of joint perturbations to data inputs as well as model weights.
arXiv Detail & Related papers (2021-02-23T20:59:30Z) - Synthetic Data and Hierarchical Object Detection in Overhead Imagery [0.0]
We develop novel synthetic data generation and augmentation techniques for enhancing low/zero-sample learning in satellite imagery.
To test the effectiveness of synthetic imagery, we employ it in the training of detection models and our two stage model, and evaluate the resulting models on real satellite images.
arXiv Detail & Related papers (2021-01-29T22:52:47Z) - Secrets of 3D Implicit Object Shape Reconstruction in the Wild [92.5554695397653]
Reconstructing high-fidelity 3D objects from sparse, partial observation is crucial for various applications in computer vision, robotics, and graphics.
Recent neural implicit modeling methods show promising results on synthetic or dense datasets.
But, they perform poorly on real-world data that is sparse and noisy.
This paper analyzes the root cause of such deficient performance of a popular neural implicit model.
arXiv Detail & Related papers (2021-01-18T03:24:48Z) - Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness [97.67477497115163]
We use mode connectivity to study the adversarial robustness of deep neural networks.
Our experiments cover various types of adversarial attacks applied to different network architectures and datasets.
Our results suggest that mode connectivity offers a holistic tool and practical means for evaluating and improving adversarial robustness.
arXiv Detail & Related papers (2020-04-30T19:12:50Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.