相关论文: Network Inversion for Generating Confidently Class…

Unsupervised transfer learning-based change detection methods exploit the feature extraction capability of pre-trained networks to distinguish changed pixels from the unchanged ones. However, their performance may vary significantly…

Change point detection (CPD) methods aim to identify abrupt shifts in the distribution of input data streams. Accurate estimators for this task are crucial across various real-world scenarios. Yet, traditional unsupervised CPD techniques…

Most Neural Networks (NNs) for classification are trained using Cross-Entropy as a loss function. This approach requires the model to have an explicit classification layer. However, there exist alternative approaches, such as Contrastive…

In the real world, a learning system could receive an input that is unlike anything it has seen during training. Unfortunately, out-of-distribution samples can lead to unpredictable behaviour. We need to know whether any given input belongs…

Counterfactually Augmented Data (CAD) involves creating new data samples by applying minimal yet sufficient modifications to flip the label of existing data samples to other classes. Training with CAD enhances model robustness against…

Current deep learning models are not designed to simultaneously address three fundamental questions: predict class labels to solve a given classification task (the "What?"), simulate changes in the situation to evaluate how this impacts…

Discriminating data classes emanating from sensors is an important problem with many applications in science and technology. We describe a new transform for pattern identification that interprets patterns as probability density functions,…

The ability to cope with out-of-distribution (OOD) corruptions and adversarial attacks is crucial in real-world safety-demanding applications. In this study, we develop a general mechanism to increase neural network robustness based on…

Probabilistic models often use neural networks to control their predictive uncertainty. However, when making out-of-distribution (OOD)} predictions, the often-uncontrollable extrapolation properties of neural networks yield poor uncertainty…

As Classifier-Free Guidance (CFG) has proven effective in conditional diffusion model sampling for improved condition alignment, many applications use a negated CFG term to filter out unwanted features from samples. However, simply negating…

Reliable confidence estimation for deep neural classifiers is a challenging yet fundamental requirement in high-stakes applications. Unfortunately, modern deep neural networks are often overconfident for their erroneous predictions. In this…

Deep neural networks tend to make overconfident predictions and often require additional detectors for misclassifications, particularly for safety-critical applications. Existing detection methods usually only focus on adversarial attacks…

Implicit generative models have the capability to learn arbitrary complex data distributions. On the downside, training requires telling apart real data from artificially-generated ones using adversarial discriminators, leading to unstable…

The starting point of our network architecture is the Credibility Transformer which extends the classical Transformer architecture by a credibility mechanism to improve model learning and predictive performance. This Credibility Transformer…

Despite high accuracy of Convolutional Neural Networks (CNNs), they are vulnerable to adversarial and out-distribution examples. There are many proposed methods that tend to detect or make CNNs robust against these fooling examples.…

Making computer-generated (CG) images more difficult to detect is an interesting problem in computer graphics and security. While most approaches focus on the image rendering phase, this paper presents a method based on increasing the…

We introduce a new attack paradigm that embeds hidden adversarial capabilities directly into diffusion models via fine-tuning, without altering their observable behavior or requiring modifications during inference. Unlike prior approaches…

Counterfactual data augmentation has recently emerged as a method to mitigate confounding biases in the training data. These biases, such as spurious correlations, arise due to various observed and unobserved confounding variables in the…

With the usage of appropriate inductive biases, Counterfactual Generative Networks (CGNs) can generate novel images from random combinations of shape, texture, and background manifolds. These images can be utilized to train an invariant…

Convolutional neural networks (CNNs) have achieved state-of-the-art performance on various tasks in computer vision. However, recent studies demonstrate that these models are vulnerable to carefully crafted adversarial samples and suffer…