Výsledky vyhledávání - "Pérez, Gustavo A."

Report

Human-in-the-Loop Visual Re-ID for Population Size Estimation

Autor: Perez, Gustavo, Sheldon, Daniel, Van Horn, Grant, Maji, Subhransu

Computer vision-based re-identification (Re-ID) systems are increasingly being deployed for estimating population size in large image collections. However, the estimated size can be significantly inaccurate when the task is challenging or when deploy

Externí odkaz: http://arxiv.org/abs/2312.05287

Zobrazit plný text záznamu

Report

DISCount: Counting in Large Image Collections with Detector-Based Importance Sampling

Autor: Perez, Gustavo, Maji, Subhransu, Sheldon, Daniel

Many modern applications use computer vision to detect and count objects in massive image collections. However, when the detection task is very difficult or in the presence of domain shifts, the counts may be inaccurate even with significant investme

Externí odkaz: http://arxiv.org/abs/2306.03151

Zobrazit plný text záznamu

Report

Domain Adaptor Networks for Hyperspectral Image Recognition

Autor: Perez, Gustavo, Maji, Subhransu

We consider the problem of adapting a network trained on three-channel color images to a hyperspectral domain with a large number of channels. To this end, we propose domain adaptor networks that map the input to be compatible with a network trained

Externí odkaz: http://arxiv.org/abs/2108.01555

Zobrazit plný text záznamu

Report

StarcNet: Machine Learning for Star Cluster Identification

Autor: Perez, Gustavo, Messa, Matteo, Calzetti, Daniela, Maji, Subhransu, Jung, Dooseok, Adamo, Angela, Siressi, Mattia

We present a machine learning (ML) pipeline to identify star clusters in the multi{color images of nearby galaxies, from observations obtained with the Hubble Space Telescope as part of the Treasury Project LEGUS (Legacy ExtraGalactic Ultraviolet Sur

Externí odkaz: http://arxiv.org/abs/2012.09327

Zobrazit plný text záznamu