Related papers: Probing Network Decisions: Capturing Uncertainties…
In this work, we for the first time present a method for detecting label errors in image datasets with semantic segmentation, i.e., pixel-wise class labels. Annotation acquisition for semantic segmentation datasets is time-consuming and…
Learning deep neural network (DNN) classifier with noisy labels is a challenging task because the DNN can easily over-fit on these noisy labels due to its high capability. In this paper, we present a very simple but effective training…
Recent deep neural networks (DNNs) can easily overfit to biased training data with noisy labels. Label correction strategy is commonly used to alleviate this issue by designing a method to identity suspected noisy labels and then correct…
We evaluate two different methods for the integration of prediction uncertainty into diagnostic image classifiers to increase patient safety in deep learning. In the first method, Monte Carlo sampling is applied with dropout at test time to…
The last decade has witnessed the proliferation of Deep Learning models in many applications, achieving unrivaled levels of predictive performance. Unfortunately, the black-box nature of Deep Learning models has posed unanswered questions…
With deep neural networks providing state-of-the-art machine learning models for numerous machine learning tasks, quantifying the robustness of these models has become an important area of research. However, most of the research literature…
Despite being effective in many application areas, Deep Neural Networks (DNNs) are vulnerable to being attacked. In object recognition, the attack takes the form of a small perturbation added to an image, that causes the DNN to misclassify,…
To understand how well a large language model captures certain semantic or syntactic features, researchers typically apply probing classifiers. However, the accuracy of these classifiers is critical for the correct interpretation of the…
Model interpretability is a requirement in many applications in which crucial decisions are made by users relying on a model's outputs. The recent movement for "algorithmic fairness" also stipulates explainability, and therefore…
This article presents the prediction difference analysis method for visualizing the response of a deep neural network to a specific input. When classifying images, the method highlights areas in a given input image that provide evidence for…
With the wide use of deep neural networks (DNN), model interpretability has become a critical concern, since explainable decisions are preferred in high-stake scenarios. Current interpretation techniques mainly focus on the feature…
Mislabeled samples are ubiquitous in real-world datasets as rule-based or expert labeling is usually based on incorrect assumptions or subject to biased opinions. Neural networks can "memorize" these mislabeled samples and, as a result,…
The problem of detecting whether a test sample is from in-distribution (i.e., training distribution by a classifier) or out-of-distribution sufficiently different from it arises in many real-world machine learning applications. However, the…
Training deep neural networks (DNNs) usually requires massive training data and computational resources. Users who cannot afford this may prefer to outsource training to a third party or resort to publicly available pre-trained models.…
Modern software systems rely on Deep Neural Networks (DNN) when processing complex, unstructured inputs, such as images, videos, natural language texts or audio signals. Provided the intractably large size of such input spaces, the…
Deep neural networks (DNNs) are increasingly being applied in malware detection and their robustness has been widely debated. Traditionally an adversarial example generation scheme relies on either detailed model information (gradient-based…
Bias in classifiers is a severe issue of modern deep learning methods, especially for their application in safety- and security-critical areas. Often, the bias of a classifier is a direct consequence of a bias in the training dataset,…
The paper proposes a new testing approach for Deep Neural Networks (DNN) using gradient-free optimization to find perturbation chains that successfully falsify the tested DNN, going beyond existing grid-based or combinatorial testing.…
Concept probing has recently garnered increasing interest as a way to help interpret artificial neural networks, dealing both with their typically large size and their subsymbolic nature, which ultimately renders them unfeasible for direct…
In this paper we present a heuristic method to provide individual explanations for those elements in a dataset (data points) which are wrongly predicted by a given classifier. Since the general case is too difficult, in the present work we…