Related papers: Semantic Segmentation of Medium-Resolution Satelli…

Many existing conditional Generative Adversarial Networks (cGANs) are limited to conditioning on pre-defined and fixed class-level semantic labels or attributes. We propose an open set GAN architecture (OpenGAN) that is conditioned…

Generative Adversarial Networks (GANs) are able to generate high-quality images, but it remains difficult to explicitly specify the semantics of synthesized images. In this work, we aim to better understand the semantic representation of…

Detecting and identifying objects in satellite images is a very challenging task: objects of interest are often very small and features can be difficult to recognize even using very high resolution imagery. For most applications, this…

Semantic segmentation is an important task in computer vision that is often tackled with convolutional neural networks (CNNs). A CNN learns to produce pixel-level predictions through training on pairs of images and their corresponding…

Training robust deep learning (DL) systems for medical image classification or segmentation is challenging due to limited images covering different disease types and severity. We propose an active learning (AL) framework to select most…

Medical anomaly detection is a critical research area aimed at recognizing abnormal images to aid in diagnosis.Most existing methods adopt synthetic anomalies and image restoration on normal samples to detect anomaly. The unlabeled data…

This paper presents a deep learning-based approach to emotion detection using Conditional Generative Adversarial Networks (cGANs). Unlike traditional unimodal techniques that rely on a single data type, we explore a multimodal framework…

Long-range contextual information is essential for achieving high-performance semantic segmentation. Previous feature re-weighting methods demonstrate that using global context for re-weighting feature channels can effectively improve the…

Generative Adversarial Networks (GANs) have recently demonstrated to successfully approximate complex data distributions. A relevant extension of this model is conditional GANs (cGANs), where the introduction of external information allows…

The usage of convolutional neural networks (CNNs) for unsupervised image segmentation was investigated in this study. In the proposed approach, label prediction and network parameter learning are alternately iterated to meet the following…

Understanding the large-scale structure of the Universe and unravelling the mysteries of dark matter are fundamental challenges in contemporary cosmology. Reconstruction of the cosmological matter distribution from lensing observables,…

Conditional Generative Adversarial Networks (cGAN) were designed to generate images based on the provided conditions, \eg, class-level distributions. However, existing methods have used the same generating architecture for all classes. This…

Neural Image Classifiers are effective but inherently hard to interpret and susceptible to adversarial attacks. Solutions to both problems exist, among others, in the form of counterfactual examples generation to enhance explainability or…

Single image super resolution (SISR) is to reconstruct a high resolution image from a single low resolution image. The SISR task has been a very attractive research topic over the last two decades. In recent years, convolutional neural…

Deep learning based image steganalysis has attracted increasing attentions in recent years. Several Convolutional Neural Network (CNN) models have been proposed and achieved state-of-the-art performances on detecting steganography. In this…

Traditional machine learning algorithms using hand-crafted feature extraction techniques (such as local binary pattern) have limited accuracy because of high variation in images of the same class (or intra-class variation) for food…

Generative Adversarial Networks (GANs) have been employed with certain success for image translation tasks between optical and real-valued SAR intensity imagery. Applications include aiding interpretability of SAR scenes with their optical…

Lack of explainability in artificial intelligence, specifically deep neural networks, remains a bottleneck for implementing models in practice. Popular techniques such as Gradient-weighted Class Activation Mapping (Grad-CAM) provide a…

Although convolutional neural networks have been proven to be an effective tool to generate high quality maps from remote sensing images, their performance significantly deteriorates when there exists a large domain shift between training…

Generative Adversarial Net (GAN) has been proven to be a powerful machine learning tool in image data analysis and generation. In this paper, we propose to use Conditional Generative Adversarial Net (CGAN) to learn and simulate time series…