Related papers: Adaptive Sensitivity Analysis for Robust Augmentat…

Neural image classifiers can often learn to make predictions by overly relying on non-predictive features that are spuriously correlated with the class labels in the training data. This leads to poor performance in real-world atypical…

This paper presents a comprehensive evaluation of instance segmentation models with respect to real-world image corruptions as well as out-of-domain image collections, e.g. images captured by a different set-up than the training dataset.…

In recent years, there has been growing concern over the vulnerability of convolutional neural networks (CNNs) to image perturbations. However, achieving general robustness against different types of perturbations remains challenging, in…

Human vision excels at segmenting visual cues without the need for explicit training, and it remains remarkably robust even as noise severity increases. In contrast, existing AI algorithms struggle to maintain accuracy under similar…

In addition to high accuracy, robustness is becoming increasingly important for machine learning models in various applications. Recently, much research has been devoted to improving the model robustness by training with noise…

Evaluation of AI systems often requires synthetic test cases, particularly for rare or safety-critical conditions that are difficult to observe in operational data. Generative AI offers a promising approach for producing such data through…

The human visual system is remarkably robust against a wide range of naturally occurring variations and corruptions like rain or snow. In contrast, the performance of modern image recognition models strongly degrades when evaluated on…

Deep neural networks are increasingly being used to detect and diagnose medical conditions using medical imaging. Despite their utility, these models are highly vulnerable to adversarial attacks and distribution shifts, which can affect…

Adversarial training suffers from robust overfitting, a phenomenon where the robust test accuracy starts to decrease during training. In this paper, we focus on both heuristics-driven and data-driven augmentations as a means to reduce…

Data augmentation is commonly used to encode invariances in learning methods. However, this process is often performed in an inefficient manner, as artificial examples are created by applying a number of transformations to all points in the…

Robustly predicting attention regions of interest for self-driving systems is crucial for driving safety but presents significant challenges due to the labor-intensive nature of obtaining large-scale attention labels and the domain gap…

We tackle here a specific, still not widely addressed aspect, of AI robustness, which consists of seeking invariance / insensitivity of model performance to hidden factors of variations in the data. Towards this end, we employ a two step…

Despite advances in deep learning, robustness under domain shift remains a major bottleneck in medical imaging settings. Findings on natural images suggest that deep neural models can show a strong textural bias when carrying out image…

Most state-of-the-art semantic segmentation approaches only achieve high accuracy in good conditions. In practically-common but less-discussed adverse environmental conditions, their performance can decrease enormously. Existing studies…

Learning-based image compression methods have emerged as state-of-the-art, showcasing higher performance compared to conventional compression solutions. These data-driven approaches aim to learn the parameters of a neural network model…

For CLIP-based prompt tuning, introducing more data as additional knowledge for enhancing fine-tuning process is proved to be an effective approach. Existing data amplification strategies for prompt tuning typically rely on external…

The paper algorithmizes the problem of regime change point identification for data measured in a system exhibiting impulsive behaviors. This is a fundamental challenge for annotation of measurement data relevant, e.g., for designing…

Robustness audits of deep neural networks (DNN) provide a means to uncover model sensitivities to the challenging real-world imaging conditions that significantly degrade DNN performance in-the-wild. Such conditions are often the result of…

Adversarial training suffers from robust overfitting, a phenomenon where the robust test accuracy starts to decrease during training. In this paper, we focus on reducing robust overfitting by using common data augmentation schemes. We…

With growing abilities of generative models, artificial content detection becomes an increasingly important and difficult task. However, all popular approaches to this problem suffer from poor generalization across domains and generative…