Related papers: Self-Challenging Improves Cross-Domain Generalizat…
The convolutional neural network (CNN) is vulnerable to degraded images with even very small variations (e.g. corrupted and adversarial samples). One of the possible reasons is that CNN pays more attention to the most discriminative…
Remote Sensing Image Captioning (RSIC) is the process of generating meaningful descriptions from remote sensing images. Recently, it has gained significant attention, with encoder-decoder models serving as the backbone for generating…
The Convolutional Neural Network (CNN) has achieved great success in image classification. The classification model can also be utilized at image or patch level for many other applications, such as object detection and segmentation. In this…
In this paper, we propose a novel convolutional neural network (CNN) architecture considering both local and global features for image enhancement. Most conventional image enhancement methods, including Retinex-based methods, cannot restore…
In many modern computer application problems, the classification of image data plays an important role. Among many different supervised machine learning models, convolutional neural networks (CNNs) and linear discriminant analysis (LDA) as…
Recently, convolutional neural network (CNN) techniques have gained popularity as a tool for hyperspectral image classification (HSIC). To improve the feature extraction efficiency of HSIC under the condition of limited samples, the current…
High content imaging assays can capture rich phenotypic response data for large sets of compound treatments, aiding in the characterization and discovery of novel drugs. However, extracting representative features from high content images…
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…
Deep artificial neural networks require a large corpus of training data in order to effectively learn, where collection of such training data is often expensive and laborious. Data augmentation overcomes this issue by artificially inflating…
Deep convolutional neural networks (CNNs) have been immensely successful in many high-level computer vision tasks given large labeled datasets. However, for video semantic object segmentation, a domain where labels are scarce, effectively…
The trend towards higher resolution remote sensing imagery facilitates a transition from land-use classification to object-level scene understanding. Rather than relying purely on spectral content, appearance-based image features come into…
Convolutional neural networks (CNNs) have been tremendously successful in solving imaging inverse problems. To understand their success, an effective strategy is to construct simpler and mathematically more tractable convolutional sparse…
During the last half decade, convolutional neural networks (CNNs) have triumphed over semantic segmentation, which is one of the core tasks in many applications such as autonomous driving and augmented reality. However, to train CNNs…
While successful for various computer vision tasks, deep neural networks have shown to be vulnerable to texture style shifts and small perturbations to which humans are robust. In this work, we show that the robustness of neural networks…
We present an approach to learn a dense pixel-wise labeling from image-level tags. Each image-level tag imposes constraints on the output labeling of a Convolutional Neural Network (CNN) classifier. We propose Constrained CNN (CCNN), a…
Despite the impressive advances achieved using deep learning for functional brain activity analysis, the heterogeneity of functional patterns and the scarcity of imaging data still pose challenges in tasks such as identifying neurological…
Convolutional Neural Networks (CNNs) significantly improve the state-of-the-art for many applications, especially in computer vision. However, CNNs still suffer from a tendency to confidently classify out-distribution samples from unknown…
CNNs with strong learning abilities are widely chosen to resolve super-resolution problem. However, CNNs depend on deeper network architectures to improve performance of image super-resolution, which may increase computational cost in…
Image colorization achieves more and more realistic results with the increasing computation power of recent deep learning techniques. It becomes more difficult to identify the fake colorized images by human eyes. In this work, we propose a…
Recent advances in unsupervised domain adaptation mainly focus on learning shared representations by global distribution alignment without considering class information across domains. The neglect of class information, however, may lead to…