Related papers: Benchmarking the Robustness of Instance Segmentati…

The integration of neural-network-based systems into clinical practice is limited by challenges related to domain generalization and robustness. The computer vision community established benchmarks such as ImageNet-C as a fundamental…

Deep neural networks have shown impressive performance for image-based disease detection. Performance is commonly evaluated through clinical validation on independent test sets to demonstrate clinically acceptable accuracy. Reporting good…

In medical image segmentation tasks, the scarcity of labeled training data poses a significant challenge when training deep neural networks. When using U-Net-style architectures, it is common practice to address this problem by pretraining…

Adversarial patches are optimized contiguous pixel blocks in an input image that cause a machine-learning model to misclassify it. However, their optimization is computationally demanding, and requires careful hyperparameter tuning,…

Deep Residual Networks present a premium in performance in comparison to conventional networks of the same depth and are trainable at extreme depths. It has recently been shown that Residual Networks behave like ensembles of relatively…

Although machine learning models typically experience a drop in performance on out-of-distribution data, accuracies on in- versus out-of-distribution data are widely observed to follow a single linear trend when evaluated across a testbed…

Motivated by the increasing popularity of transformers in computer vision, in recent times there has been a rapid development of novel architectures. While in-domain performance follows a constant, upward trend, properties like robustness…

The generalization capability of neural networks across domains is crucial for real-world applications. We argue that a generalized object recognition system should well understand the relationships among different images and also the…

We describe how randomized benchmarking can be used to reconstruct the unital part of any trace-preserving quantum map, which in turn is sufficient for the full characterization of any unitary evolution, or more generally, any unital…

We introduce a set of image transformations that can be used as corruptions to evaluate the robustness of models as well as data augmentation mechanisms for training neural networks. The primary distinction of the proposed transformations…

Image colorization is inherently an ill-posed problem with multi-modal uncertainty. Previous methods leverage the deep neural network to map input grayscale images to plausible color outputs directly. Although these learning-based methods…

This article presents an efficient end-to-end method to perform instance-level recognition employed to the task of labeling and ranking landmark images. In a first step, we embed images in a high dimensional feature space using…

Various normalization layers have been proposed to help the training of neural networks. Group Normalization (GN) is one of the effective and attractive studies that achieved significant performances in the visual recognition task. Despite…

Synthetic corruptions gathered into a benchmark are frequently used to measure neural network robustness to distribution shifts. However, robustness to synthetic corruption benchmarks is not always predictive of robustness to distribution…

Object detection or localization is an incremental step in progression from coarse to fine digital image inference. It not only provides the classes of the image objects, but also provides the location of the image objects which have been…

Recent studies have shown that higher accuracy on ImageNet usually leads to better robustness against different corruptions. Therefore, in this paper, instead of following the traditional research paradigm that investigates new…

Batch Normalization (BatchNorm) is effective for improving the performance and accelerating the training of deep neural networks. However, it has also shown to be a cause of adversarial vulnerability, i.e., networks without it are more…

Can pretrained models generalize to new datasets without any retraining? We deploy pretrained image models on datasets they were not trained for, and investigate whether their embeddings form meaningful clusters. Our suite of benchmarking…

Neural networks have revolutionized various domains, exhibiting remarkable accuracy in tasks like natural language processing and computer vision. However, their vulnerability to slight alterations in input samples poses challenges,…

Instance segmentation is the problem of detecting and delineating each distinct object of interest appearing in an image. Current instance segmentation approaches consist of ensembles of modules that are trained independently of each other,…