Related papers: Permuted AdaIN: Reducing the Bias Towards Global S…

We address the problem of camera pose estimation in visual localization. Current regression-based methods for pose estimation are trained and evaluated scene-wise. They depend on the coordinate frame of the training dataset and show a low…

Most existing studies on unsupervised domain adaptation (UDA) assume that each domain's training samples come with domain labels (e.g., painting, photo). Samples from each domain are assumed to follow the same distribution and the domain…

We introduce a new architecture called a conditional invertible neural network (cINN), and use it to address the task of diverse image-to-image translation for natural images. This is not easily possible with existing INN models due to some…

Convolutional Neural Networks (CNNs) are widely assumed to be translation-invariant, yet standard architectures exhibit a startling fragility: even a single-pixel shift can drastically degrade performance due to their reliance on spatially…

Machine understanding of complex images is a key goal of artificial intelligence. One challenge underlying this task is that visual scenes contain multiple inter-related objects, and that global context plays an important role in…

Many problems in computer vision require dealing with sparse, unordered data in the form of point clouds. Permutation-equivariant networks have become a popular solution-they operate on individual data points with simple perceptrons and…

We introduce style augmentation, a new form of data augmentation based on random style transfer, for improving the robustness of convolutional neural networks (CNN) over both classification and regression based tasks. During training, our…

Arbitrary style transfer holds widespread attention in research and boasts numerous practical applications. The existing methods, which either employ cross-attention to incorporate deep style attributes into content attributes or use…

Diffusion models have shown significant progress in image translation tasks recently. However, due to their stochastic nature, there's often a trade-off between style transformation and content preservation. Current strategies aim to…

Image quality databases are used to train models for predicting subjective human perception. However, most existing databases focus on distortions commonly found in digital media and not in natural conditions. Affine transformations are…

The robustness of image classifiers is essential to their deployment in the real world. The ability to assess this resilience to manipulations or deviations from the training data is thus crucial. These modifications have traditionally…

Interpreting neural network classifiers using gradient-based saliency maps has been extensively studied in the deep learning literature. While the existing algorithms manage to achieve satisfactory performance in application to standard…

We introduce NaturalInversion, a novel model inversion-based method to synthesize images that agrees well with the original data distribution without using real data. In NaturalInversion, we propose: (1) a Feature Transfer Pyramid which…

Time series forecasting under distribution shift remains challenging, as existing deep learning models often rely on local statistical normalization (e.g., mean and variance) that fails to capture global distribution shift. Methods like…

In recent years, the emergence of deep convolutional neural networks has positioned face recognition as a prominent research focus in computer vision. Traditional loss functions, such as margin-based, hard-sample mining-based, and hybrid…

We propose a novel domain generalization technique, referred to as Randomized Adversarial Style Perturbation (RASP), which is motivated by the observation that the characteristics of each domain are captured by the feature statistics…

We propose a universal background subtraction framework based on the Arithmetic Distribution Neural Network (ADNN) for learning the distributions of temporal pixels. In our ADNN model, the arithmetic distribution operations are utilized to…

We present an approach to learning regular spatial transformations between image pairs in the context of medical image registration. Contrary to optimization-based registration techniques and many modern learning-based methods, we do not…

Denoising diffusion models have recently achieved remarkable success in image generation, capturing rich information about natural image statistics. This makes them highly promising for image reconstruction, where the goal is to recover a…

Though deep neural networks have achieved impressive success on various vision tasks, obvious performance degradation still exists when models are tested in out-of-distribution scenarios. In addressing this limitation, we ponder that the…