Related papers: Dilated Convolution with Learnable Spacings makes …

Deep learning based methods hold state-of-the-art results in image denoising, but remain difficult to interpret due to their construction from poorly understood building blocks such as batch-normalization, residual learning, and feature…

Large-scale vision-language models (VLMs), such as CLIP, have achieved remarkable success in zero-shot learning (ZSL) by leveraging large-scale visual-text pair datasets. However, these methods often lack interpretability, as they compute…

Planet-scale photo geolocalization involves the intricate task of estimating the geographic location depicted in an image purely based on its visual features. While deep learning models, particularly convolutional neural networks (CNNs),…

Low-dose CT denoising is a challenging task that has been studied by many researchers. Some studies have used deep neural networks to improve the quality of low-dose CT images and achieved fruitful results. In this paper, we propose a deep…

Apart from discriminative models for classification and object detection tasks, the application of deep convolutional neural networks to basic research utilizing natural imaging data has been somewhat limited; particularly in cases where a…

Ensembles of Convolutional neural networks have shown remarkable results in learning discriminative semantic features for image classification tasks. Though, the models in the ensemble often concentrate on similar regions in images. This…

Deep Convolutional Neural Networks (DCNNs) were originally inspired by principles of biological vision, have evolved into best current computational models of object recognition, and consequently indicate strong architectural and functional…

In this paper two new learning-based eXplainable AI (XAI) methods for deep convolutional neural network (DCNN) image classifiers, called L-CAM-Fm and L-CAM-Img, are proposed. Both methods use an attention mechanism that is inserted in the…

We propose a novel approach to image classification inspired by complex nonlinear biological visual processing, whereby classical convolutional neural networks (CNNs) are equipped with learnable higher-order convolutions. Our model…

The emerging Learned Compression (LC) replaces the traditional codec modules with Deep Neural Networks (DNN), which are trained end-to-end for rate-distortion performance. This approach is considered as the future of image/video…

Human-centric explainability of AI-based Decision Support Systems (DSS) using visual input modalities is directly related to reliability and practicality of such algorithms. An otherwise accurate and robust DSS might not enjoy trust of…

In this paper, we propose to exploit the rich hierarchical features of deep convolutional neural networks to improve the accuracy and robustness of visual tracking. Deep neural networks trained on object recognition datasets consist of…

We introduce Region-Aware Deformable Convolution (RAD-Conv), a new convolutional operator that enhances neural networks' ability to adapt to complex image structures. Unlike traditional deformable convolutions, which are limited to fixed…

Despite the large augmentation family, only a few cherry-picked robust augmentation policies are beneficial to self-supervised image representation learning. In this paper, we propose a directional self-supervised learning paradigm (DSSL),…

In this work we establish the relation between optimal control and training deep Convolution Neural Networks (CNNs). We show that the forward propagation in CNNs can be interpreted as a time-dependent nonlinear differential equation and…

Discriminative correlation filters (DCFs) have been shown to perform superiorly in visual tracking. They only need a small set of training samples from the initial frame to generate an appearance model. However, existing DCFs learn the…

Discrete choice models (DCMs) are used to analyze individual decision-making in contexts such as transportation choices, political elections, and consumer preferences. DCMs play a central role in applied econometrics by enabling inference…

Hallucination mitigation remains a persistent challenge for large language models (LLMs), even as model scales grow. Existing approaches often rely on external knowledge sources, such as structured databases or knowledge graphs, accessed…

Vision-language models (VLMs) have shown promise in 2D medical image analysis, but extending them to 3D remains challenging due to the high computational demands of volumetric data and the difficulty of aligning 3D spatial features with…

In recent years, coordinate-based neural implicit representations have shown promising results for the task of Simultaneous Localization and Mapping (SLAM). While achieving impressive performance on small synthetic scenes, these methods…