A Survey on the Robustness of Computer Vision Models against Common Corruptions
This is an incremental survey that synthesizes existing research to highlight inconsistencies and provide a benchmark for improving model robustness against common corruptions, targeting researchers and practitioners in computer vision.
This survey addresses the problem of computer vision models being vulnerable to common corruptions like noise and blur, which reduces reliability in real-world applications, by providing a comprehensive overview of methods to improve robustness and releasing a benchmark framework that reveals corruption robustness does not scale with model size or data size, with large models showing negligible improvements despite higher computational costs.
The performance of computer vision models are susceptible to unexpected changes in input images caused by sensor errors or extreme imaging environments, known as common corruptions (e.g. noise, blur, illumination changes). These corruptions can significantly hinder the reliability of these models when deployed in real-world scenarios, yet they are often overlooked when testing model generalization and robustness. In this survey, we present a comprehensive overview of methods that improve the robustness of computer vision models against common corruptions. We categorize methods into three groups based on the model components and training methods they target: data augmentation, learning strategies, and network components. We release a unified benchmark framework (available at \url{https://github.com/nis-research/CorruptionBenchCV}) to compare robustness performance across several datasets, and we address the inconsistencies of evaluation practices in the literature. Our experimental analysis highlights the base corruption robustness of popular vision backbones, revealing that corruption robustness does not necessarily scale with model size and data size. Large models gain negligible robustness improvements, considering the increased computational requirements. To achieve generalizable and robust computer vision models, we foresee the need of developing new learning strategies that efficiently exploit limited data and mitigate unreliable learning behaviors.