Related papers: Combining statistical learning with deep learning …

Despite recent breakthroughs in deep learning methods for image lighting enhancement, they are inferior when applied to portraits because 3D facial information is ignored in their models. To address this, we present a novel deep learning…

A key challenge of high contrast imaging (HCI) is to differentiate a speckle from an exoplanet signal. The sources of speckles are a combination of atmospheric residuals and aberrations in the non-common path. Those non-common path…

Supervised deep networks are among the best methods for finding correspondences in stereo image pairs. Like all supervised approaches, these networks require ground truth data during training. However, collecting large quantities of…

The joint hyperspectral image (HSI) and LiDAR data classification aims to interpret ground objects at more detailed and precise level. Although deep learning methods have shown remarkable success in the multisource data classification task,…

Anomaly detection on the attributed network has recently received increasing attention in many research fields, such as cybernetic anomaly detection and financial fraud detection. With the wide application of deep learning on graph…

Learning node-level representations of heterophilic graphs is crucial for various applications, including fraudster detection and protein function prediction. In such graphs, nodes share structural similarity identified by the equivalence…

Learning local descriptors is an important problem in computer vision. While there are many techniques for learning local patch descriptors for 2D images, recently efforts have been made for learning local descriptors for 3D points. The…

Pre-training a recognition model with contrastive learning on a large dataset of unlabeled data has shown great potential to boost the performance of a downstream task, e.g., image classification. However, in domains such as medical…

Machine Learning is an efficient method for analyzing and interpreting the increasing amount of astronomical data that is available. In this study, we show, a pedagogical approach that should benefit anyone willing to experiment with Deep…

Intermediate features at different layers of a deep neural network are known to be discriminative for visual patterns of different complexities. However, most existing works ignore such cross-layer heterogeneities when classifying samples…

A recent class of hyperspectral anomaly detection methods can be trained once on background datasets and then deployed universally without per-scene retraining or parameter tuning, showing strong efficiency and robustness. Building upon…

Fine-tuning a pre-trained language model via the contrastive learning framework with a large amount of unlabeled sentences or labeled sentence pairs is a common way to obtain high-quality sentence representations. Although the contrastive…

Learning-based lossless image compression employs pixel-based or subimage-based auto-regression for probability estimation, which achieves desirable performances. However, the existing works only consider context dependencies in one…

State-of-the-art image models predominantly follow a two-stage strategy: pre-training on large datasets and fine-tuning with cross-entropy loss. Many studies have shown that using cross-entropy can result in sub-optimal generalisation and…

The high contrast and spatial resolution requirements for directly imaging exoplanets requires effective coordination of wavefront control, coronagraphy, observation techniques, and post-processing algorithms. However, even with this suite…

State-of-the-art object detection methods applied to satellite and drone imagery largely fail to identify small and dense objects. One reason is the high variability of content in the overhead imagery due to the terrestrial region captured…

Convolutional Neural Networks (CNNs) have become deeper and more complicated compared with the pioneering AlexNet. However, current prevailing training scheme follows the previous way of adding supervision to the last layer of the network…

Although graph neural networks (GNNs) have achieved impressive achievements in graph classification, they often need abundant task-specific labels, which could be extensively costly to acquire. A credible solution is to explore additional…

Predicting whether a treatment leads to meaningful improvement is a central challenge in personalized medicine, particularly when disease progression manifests as subtle visual changes over time. While data-driven deep learning (DL) offers…

Feature matters. How to train a deep network to acquire discriminative features across categories and polymerized features within classes has always been at the core of many computer vision tasks, specially for large-scale recognition…