Related papers: Attention-Based Preprocessing Framework for Improv…

We study how to leverage Web images to augment human-curated object detection datasets. Our approach is two-pronged. On the one hand, we retrieve Web images by image-to-image search, which incurs less domain shift from the curated data than…

In the era of large all-sky surveys, there will be a need for rapid, automatic classifications of newly discovered transient objects. Our focus here is the classification of supernovae (SNe). We consider random forest machine learning…

Downsampling is widely adopted to achieve a good trade-off between accuracy and latency for visual recognition. Unfortunately, the commonly used pooling layers are not learned, and thus cannot preserve important information. As another…

We apply deep recurrent neural networks, which are capable of learning complex sequential information, to classify supernovae\footnote{Code available at \href{https://github.com/adammoss/supernovae}{https://github.com/adammoss/supernovae}}.…

We present GHOST, a database of 16,175 spectroscopically classified supernovae and the properties of their host galaxies. We have developed a host galaxy association method using image gradients that achieves fewer misassociations for low-z…

In surveillance, monitoring and tactical reconnaissance, gathering the right visual information from a dynamic environment and accurately processing such data are essential ingredients to making informed decisions which determines the…

Although deep learning based models for underwater image enhancement have achieved good performance, they face limitations in both lightweight and effectiveness, which prevents their deployment and application on resource-constrained…

Painting classification plays a vital role in organizing, finding, and suggesting artwork for digital and classic art galleries. Existing methods struggle with adapting knowledge from the real world to artistic images during training,…

Traditional deep learning-based object detection networks often resize images during the data preprocessing stage to achieve a uniform size and scale in the feature map. Resizing is done to facilitate model propagation and fully connected…

Self-supervised learning algorithms (SSL) based on instance discrimination have shown promising results, performing competitively or even outperforming supervised learning counterparts in some downstream tasks. Such approaches employ data…

When performing data classification over a stream of continuously occurring instances, a key challenge is to develop an open-world classifier that anticipates instances from an unknown class. Studies addressing this problem, typically…

Wide field small aperture telescopes are working horses for fast sky surveying. Transient discovery is one of their main tasks. Classification of candidate transient images between real sources and artifacts with high accuracy is an…

Upcoming astronomical surveys such as the Large Synoptic Survey Telescope (LSST) will rely on photometric classification to identify the majority of the transients and variables that they discover. We present a set of techniques for…

Self-supervised Learning (SSL) including the mainstream contrastive learning has achieved great success in learning visual representations without data annotations. However, most methods mainly focus on the instance level information (\ie,…

Large modern surveys require efficient review of data in order to find transient sources such as supernovae, and to distinguish such sources from artefacts and noise. Much effort has been put into the development of automatic algorithms,…

Deep neural networks demonstrate to have a high performance on image classification tasks while being more difficult to train. Due to the complexity and vanishing gradient problem, it normally takes a lot of time and more computational…

In November 2019 we began operating FLEET (Finding Luminous and Exotic Extragalactic Transients), a machine learning algorithm designed to photometrically identify Type I superluminous supernovae (SLSNe) in transient alert streams. Using…

We propose a framework for top-down salient object detection that incorporates a tightly coupled image classification module. The classifier is trained on novel category-aware sparse codes computed on object dictionaries used for saliency…

We describe an iterative active-learning algorithm to recognise rare traffic signs. A standard ResNet is trained on a training set containing only a single sample of the rare class. We demonstrate that by sorting the samples of a large,…

Accurate classification of breast ultrasound images into benign, malignant, and normal categories is a critical clinical task complicated by speckle noise, acoustic shadowing, and inter-class visual ambiguity. Existing deep learning methods…