Related papers: Towards Improved Input Masking for Convolutional N…

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…

Masked reconstruction serves as a fundamental pretext task for self-supervised learning, enabling the model to enhance its feature extraction capabilities by reconstructing the masked segments from extensive unlabeled data. In human…

It is important to learn various types of classifiers given training data with noisy labels. Noisy labels, in the most popular noise model hitherto, are corrupted from ground-truth labels by an unknown noise transition matrix. Thus, by…

Visualizing a large-scale volumetric dataset with high resolution is challenging due to the substantial computational time and space complexity. Recent deep learning-based image inpainting methods significantly improve rendering latency by…

Deep image generation is becoming a tool to enhance artists and designers creativity potential. In this paper, we aim at making the generation process more structured and easier to interact with. Inspired by vector graphics systems, we…

Visible watermark removal which involves watermark cleaning and background content restoration is pivotal to evaluate the resilience of watermarks. Existing deep neural network (DNN)-based models still struggle with large-area watermarks…

In this paper, we address the problem of estimating and removing non-uniform motion blur from a single blurry image. We propose a deep learning approach to predicting the probabilistic distribution of motion blur at the patch level using a…

Real-world face detection and alignment demand an advanced discriminative model to address challenges by pose, lighting and expression. Illuminated by the deep learning algorithm, some convolutional neural networks based face detection and…

All datasets contain some biases, often unintentional, due to how they were acquired and annotated. These biases distort machine-learning models' performance, creating spurious correlations that the models can unfairly exploit, or,…

We propose a new algorithm to learn a one-hidden-layer convolutional neural network where both the convolutional weights and the outputs weights are parameters to be learned. Our algorithm works for a general class of (potentially…

This work explores the biases in learning processes based on deep neural network architectures. We analyze how bias affects deep learning processes through a toy example using the MNIST database and a case study in gender detection from…

In the recent years, public use of artistic effects for editing and beautifying images has encouraged researchers to look for new approaches to this task. Most of the existing methods apply artistic effects to the whole image. Exploitation…

Hyperparameters tuning is a time-consuming approach, particularly when the architecture of the neural network is decided as part of this process. For instance, in convolutional neural networks (CNNs), the selection of the number and the…

Image inpainting is an ill-posed problem to recover missing or damaged image content based on incomplete images with masks. Previous works usually predict the auxiliary structures (e.g., edges, segmentation and contours) to help fill…

Depth maps are used in a wide range of applications from 3D rendering to 2D image effects such as Bokeh. However, those predicted by single image depth estimation (SIDE) models often fail to capture isolated holes in objects and/or have…

Most dense recognition approaches bring a separate decision in each particular pixel. These approaches deliver competitive performance in usual closed-set setups. However, important applications in the wild typically require strong…

Person retrieval faces many challenges including cluttered background, appearance variations (e.g., illumination, pose, occlusion) among different camera views and the similarity among different person's images. To address these issues, we…

In this paper, we introduce the \textit{Layer-Peeled Model}, a nonconvex yet analytically tractable optimization program, in a quest to better understand deep neural networks that are trained for a sufficiently long time. As the name…

The need for a large amount of labeled data in the supervised setting has led recent studies to utilize self-supervised learning to pre-train deep neural networks using unlabeled data. Many self-supervised training strategies have been…

When optimizing convolutional neural networks (CNN) for a specific image-based task, specialists commonly overshoot the number of convolutional layers in their designs. By implication, these CNNs are unnecessarily resource intensive to…