Related papers: Enhanced Model Robustness to Input Corruptions by …

For effective autonomous navigation,estimation of the pose of the robot is essential at every sampling time. For computing an accurate estimation,odometric error needs to be reduced with the help of data from external sensor. In this work,…

As self-driving technology advances toward widespread adoption, determining safe operational thresholds across varying environmental conditions becomes critical for public safety. This paper proposes a method for evaluating the robustness…

The popularity of high and ultra-high definition displays has led to the need for methods to improve the quality of videos already obtained at much lower resolutions. Current Video Super-Resolution methods are not robust to mismatch between…

Radio Access Network (RAN) systems are inherently complex, requiring continuous monitoring to prevent performance degradation and ensure optimal user experience. The RAN leverages numerous key performance indicators (KPIs) to evaluate…

Adversarial images are designed to mislead deep neural networks (DNNs), attracting great attention in recent years. Although several defense strategies achieved encouraging robustness against adversarial samples, most of them fail to…

We introduce the MNIST-C dataset, a comprehensive suite of 15 corruptions applied to the MNIST test set, for benchmarking out-of-distribution robustness in computer vision. Through several experiments and visualizations we demonstrate that…

The state-of-the-art deep neural networks are vulnerable to common corruptions (e.g., input data degradations, distortions, and disturbances caused by weather changes, system error, and processing). While much progress has been made in…

Corruptions due to data perturbations and label noise are prevalent in the datasets from unreliable sources, which poses significant threats to model training. Despite existing efforts in developing robust models, current learning methods…

Automotive scene understanding under adverse weather conditions raises a realistic and challenging problem attributable to poor outdoor scene visibility (e.g. foggy weather). However, because most contemporary scene understanding approaches…

Archetypal scenarios for change detection generally consider two images acquired through sensors of the same modality. However, in some specific cases such as emergency situations, the only images available may be those acquired through…

Transformation invariances are present in many real-world problems. For example, image classification is usually invariant to rotation and color transformation: a rotated car in a different color is still identified as a car. Data…

Because of the increasing accuracy of Deep Neural Networks (DNNs) on different tasks, a lot of real times systems are utilizing DNNs. These DNNs are vulnerable to adversarial perturbations and corruptions. Specifically, natural corruptions…

Pretrained vision-language models such as CLIP achieve strong zero-shot generalization but remain vulnerable to distribution shifts caused by input corruptions. In this work, we investigate how corruptions affect CLIP's image embeddings and…

We propose a strategy for improving camera location estimation in structure from motion. Our setting assumes highly corrupted pairwise directions (i.e., normalized relative location vectors), so there is a clear room for improving current…

Pansharpening is a crucial task in remote sensing, enabling the generation of high-resolution multispectral images by fusing low-resolution multispectral data with high-resolution panchromatic images. This paper provides a comprehensive…

Recent research has made the surprising finding that state-of-the-art deep learning models sometimes fail to generalize to small variations of the input. Adversarial training has been shown to be an effective approach to overcome this…

Most existing deep learning-based pan-sharpening methods have several widely recognized issues, such as spectral distortion and insufficient spatial texture enhancement, we propose a novel pan-sharpening convolutional neural network based…

Generative models are widely employed to enhance the photorealism of visual synthetic data for training computer vision algorithms. However, they often introduce visual artifacts that degrade the accuracy of these algorithms and require…

In recent years, significant progress has been achieved for 3D object detection on point clouds thanks to the advances in 3D data collection and deep learning techniques. Nevertheless, 3D scenes exhibit a lot of variations and are prone to…

AI-generated image detectors suffer significant performance degradation under real-world image corruptions such as JPEG compression, Gaussian blur, and resolution downsampling. We observe that state-of-the-art methods, including B-Free,…