Related papers: deep PACO: Combining statistical models with deep …

We define the object detection from imagery problem as estimating a very large but extremely sparse bounding box dependent probability distribution. Subsequently we identify a sparse distribution estimation scheme, Directed Sparse Sampling,…

Direct imaging of Earth-like planets is one of the main science cases for the next generation of extremely large telescopes. This is very challenging due to the star-planet contrast that must be overcome. Most current high-contrast imaging…

Deep learning has potential to automate screening, monitoring and grading of disease in medical images. Pretraining with contrastive learning enables models to extract robust and generalisable features from natural image datasets,…

Salient object detection has recently witnessed substantial progress due to powerful features extracted using deep convolutional neural networks (CNNs). However, existing CNN-based methods operate at the patch level instead of the pixel…

Convolutional neural networks (CNNs) are one of the most effective deep learning methods to solve image classification problems, but the best architecture of a CNN to solve a specific problem can be extremely complicated and hard to design.…

This tutorial is an introduction to High-Contrast Imaging, a technique that enables astronomers to isolate light from faint planets and/or circumstellar disks that would otherwise be lost amidst the light of their host stars. Although…

With the advancement of aerospace technology and the increasing demands of military applications, the development of low false-alarm and high-precision infrared small target detection algorithms has emerged as a key focus of research…

Automatic Check-Out (ACO) receives increased interests in recent years. An important component of the ACO system is the visual item counting, which recognizes the categories and counts of the items chosen by the customers. However, the…

The advent of high-contrast imaging instruments combined with medium-resolution spectrographs allows spectral and temporal dimensions to be combined with spatial dimensions to detect and potentially characterize exoplanets with higher…

Image search can be tackled using deep features from pre-trained Convolutional Neural Networks (CNN). The feature map from the last convolutional layer of a CNN encodes descriptive information from which a discriminative global descriptor…

Context. Direct imaging of exoplanets takes advantage of state-of-the-art adaptive optics (AO) systems, coronagraphy, and post-processing techniques. Coronagraphs attenuate starlight to mitigate the unfavorable flux ratio between an…

Most of previous deepfake detection researches bent their efforts to describe and discriminate artifacts in human perceptible ways, which leave a bias in the learned networks of ignoring some critical invariance features intra-class and…

Convolutional neural networks (CNN) have demonstrated remarkable performance when the training and testing data are from the same distribution. However, such trained CNN models often largely degrade on testing data which is unseen and…

Multiple objective assessment of image-quality-based studies have reported that several deep-learning-based denoising methods show limited performance on signal-detection tasks. Our goal was to investigate the reasons for this limited…

We develop a Learning Direct Optimization (LiDO) method for the refinement of a latent variable model that describes input image x. Our goal is to explain a single image x with an interpretable 3D computer graphics model having scene graph…

We introduce NeCo: Patch Neighbor Consistency, a novel self-supervised training loss that enforces patch-level nearest neighbor consistency across a student and teacher model. Compared to contrastive approaches that only yield binary…

In the last decade, over a million stars were monitored to detect transiting planets. Manual interpretation of potential exoplanet candidates is labor intensive and subject to human error, the results of which are difficult to quantify.…

Direct imaging of extra-solar planets has now become a reality, especially with the deployment and commissioning of the first generation of specialized ground-based instruments such as the GPI, SPHERE, P1640 and SCExAO. These systems will…

Self-supervised representation learning is a critical problem in computer vision, as it provides a way to pretrain feature extractors on large unlabeled datasets that can be used as an initialization for more efficient and effective…

Deep learning in medical imaging has the potential to minimize the risk of diagnostic errors, reduce radiologist workload, and accelerate diagnosis. Training such deep learning models requires large and accurate datasets, with annotations…