Related papers: Attention-Based Preprocessing Framework for Improv…

It is challenging to train a robust object detector under the supervised learning setting when the annotated data are scarce. Thus, previous approaches tackling this problem are in two categories: semi-supervised learning models that…

Video salient object detection models trained on pixel-wise dense annotation have achieved excellent performance, yet obtaining pixel-by-pixel annotated datasets is laborious. Several works attempt to use scribble annotations to mitigate…

We present algorithms and software for constructing high-precision difference images to detect and measure transients, such as microlensing events, in crowded stellar fields using the Nancy Grace Roman Space Telescope. Our method generates…

Topological data analysis (TDA) is a relatively new field that is gaining rapid adoption due to its robustness and ability to effectively describe complex datasets by quantifying geometric information. In imaging contexts, TDA typically…

New time-domain surveys, such as the Vera C. Rubin Observatory Legacy Survey of Space and Time (LSST), will observe millions of transient alerts each night, making standard approaches of visually identifying new and interesting transients…

This paper studies a combined person reidentification (re-id) method that uses human parsing, analytical feature extraction and similarity estimation schemes. One of its prominent features is its low computational requirements so it can be…

State-of-the-art 3D object detectors are usually trained on large-scale datasets with high-quality 3D annotations. However, such 3D annotations are often expensive and time-consuming, which may not be practical for real applications. A…

We present a new method for probabilistically classifying supernovae (SNe) without using SN spectral or photometric data. Unlike all previous studies to classify SNe without spectra, this technique does not use any SN photometry. Instead,…

Redshift measurement has always been a constant need in modern astronomy and cosmology. And as new surveys have been providing an immense amount of data on astronomical objects, the need to process such data automatically proves to be…

We describe the difference imaging pipeline (DiffImg) used to detect transients in deep images from the Dark Energy Survey Supernova program (DES-SN) in its first observing season from Aug 2013 through Feb 2014. DES-SN is a search for…

Restoring images from low-light data is a challenging problem. Most existing deep-network based algorithms are designed to be trained with pairwise images. Due to the lack of real-world datasets, they usually perform poorly when generalized…

Strongly gravitationally lensed supernovae (LSNe) are promising probes for providing absolute distance measurements using gravitational-lens time delays. Spatially unresolved LSNe offer an opportunity to enhance the sample size for…

Labeling medical images depends on professional knowledge, making it difficult to acquire large amount of annotated medical images with high quality in a short time. Thus, making good use of limited labeled samples in a small dataset to…

Low-light images often suffer from limited visibility and multiple types of degradation, rendering low-light image enhancement (LIE) a non-trivial task. Some endeavors have been recently made to enhance low-light images using convolutional…

Unsupervised anomaly detection aims to build models to effectively detect unseen anomalies by only training on the normal data. Although previous reconstruction-based methods have made fruitful progress, their generalization ability is…

We aim to localize objects in images using image-level supervision only. Previous approaches to this problem mainly focus on discriminative object regions and often fail to locate precise object boundaries. We address this problem by…

The progenitors for many types of supernovae (SNe) are still unknown, and an approach to diagnose their physical origins is to investigate the light curve brightness and shape of a large set of SNe. However, it is often difficult to compare…

Classifying transients based on multi band light curves is a challenging but crucial problem in the era of GAIA and LSST since the sheer volume of transients will make spectroscopic classification unfeasible. Here we present a nonparametric…

Reconstruction-based approaches to anomaly detection tend to fall short when applied to complex datasets with target classes that possess high inter-class variance. Similar to the idea of self-taught learning used in transfer learning, many…

Salient object detection (SOD) is a fundamental computer vision task. Recently, with the revival of deep neural networks, SOD has made great progresses. However, there still exist two thorny issues that cannot be well addressed by existing…