Related papers: Faster ISNet for Background Bias Mitigation on Dee…

Recently, deep neural networks have demonstrated excellent performances in recognizing the age and gender on human face images. However, these models were applied in a black-box manner with no information provided about which facial…

Common approaches to explainable AI (XAI) for deep learning focus on analyzing the importance of input features on the classification task in a given model: saliency methods like SHAP and GradCAM are used to measure the impact of spatial…

In this work, we study the problem of non-blind image deconvolution and propose a novel recurrent network architecture that leads to very competitive restoration results of high image quality. Motivated by the computational efficiency and…

Deep neural networks demonstrate to have a high performance on image classification tasks while being more difficult to train. Due to the complexity and vanishing gradient problem, it normally takes a lot of time and more computational…

Neural networks often exhibit simplicity bias, favoring simpler features over more complex ones, even when both are equally predictive. We introduce a novel method called imbalanced label coupling to explore and extend this simplicity bias…

Image super-resolution (SR) has witnessed extensive neural network designs from CNN to transformer architectures. However, prevailing SR models suffer from prohibitive memory footprint and intensive computations, which limits further…

CNNs have become one of the most commonly used computational tool in the past two decades. One of the primary downsides of CNNs is that they work as a ``black box", where the user cannot necessarily know how the image data are analyzed, and…

Deep neural networks have achieved remarkable success in single image super-resolution (SISR). The computing and memory requirements of these methods have hindered their application to broad classes of real devices with limited computing…

Deep convolutional neural networks (CNNs) with strong expressive ability have achieved impressive performances on single image super-resolution (SISR). However, their excessive amounts of convolutions and parameters usually consume high…

Background subtraction is a fundamental task in computer vision with numerous real-world applications, ranging from object tracking to video surveillance. Dynamic backgrounds poses a significant challenge here. Supervised deep…

Training very deep convolutional networks is challenging, requiring significant computational resources and time. Existing acceleration methods often depend on specific architectures or require network modifications. We introduce…

The approximation of nonlinear kernels via linear feature maps has recently gained interest due to their applications in reducing the training and testing time of kernel-based learning algorithms. Current random projection methods avoid the…

For current and future neutrino oscillation experiments using large Liquid Argon Time Projection Chambers (LAr-TPCs), a key challenge is identifying neutrino interactions from the pervading cosmic-ray background. Rejection of such…

Deep neural networks tend to underestimate uncertainty and produce overly confident predictions. Recently proposed solutions, such as MC Dropout and SDENet, require complex training and/or auxiliary out-of-distribution data. We propose a…

High Resolution Range Profiles (HRRP) have become a key area of focus in the domain of Radar Automatic Target Recognition (RATR). Despite the success of deep learning based HRRP recognition, these methods needs a large amount of training…

Night Photography Rendering (NPR) poses a significant challenge due to the extreme contrast between dark and illuminated areas in scenes, stemming from concurrent capture of severely dark regions alongside intense point light sources.…

Shortcut learning, where machine learning models exploit spurious correlations in data instead of capturing meaningful features, poses a significant challenge to building robust and generalizable models. This phenomenon is prevalent across…

Hyperspectral image (HSI) classification faces critical challenges, including high spectral dimensionality, complex spectral-spatial correlations, and limited training samples with severe class imbalance. While CNNs excel at local feature…

Geometric shape features have been widely used as strong predictors for image classification. Nevertheless, most existing classifiers such as deep neural networks (DNNs) directly leverage the statistical correlations between these shape…

The incessant advent of online services demands high speed and efficient recommender systems (ReS) that can maintain real-time performance along with processing very complex user-item interactions. The present study, therefore, considers…