Grace Vincent

Electrl & Comp Engr Grad &Temp

Works (3)

Updated: April 5th, 2024 17:56

2023 article

CLOVER: Contrastive Learning for Onboard Vision-Enabled Robotics

Vincent, G. M., Ward, I. R., Moore, C., Chen, J., Pak, K., Yepremyan, A., … Goh, E. Y. (2023, December 19). JOURNAL OF SPACECRAFT AND ROCKETS.

By: G. Vincent n, I. Ward *, C. Moore, J. Chen, K. Pak, A. Yepremyan, B. Wilson, E. Goh

author keywords: Robotics; Planets; Convolutional Neural Network; Computer Vision; Planetary Science and Exploration; Uncrewed Spacecraft; Remote Sensing and Applications; Representation Learning; Mars Science Laboratory; Mars Exploration Rover
TL;DR: A self-supervised learning (SSL) framework is proposed that leverages contrastive learning techniques to improve upon state-of-the-art performance on several published Mars computer vision benchmarks and investigates the importance of dataset heterogeneity in mixed-domain contrastive pretraining. (via Semantic Scholar)
Source: Web Of Science
Added: January 16, 2024

2023 article

Self-supervised Distillation for Computer Vision Onboard Planetary Robots

2023 IEEE AEROSPACE CONFERENCE.

By: E. Goh *, I. Ward *, G. Vincent n, K. Pak *, J. Chen * & B. Wilson *

TL;DR: Results indicate that self-supervised distillation enables small models to achieve state-of-the-art performance on the benchmark datasets, supporting the feasibility of performing real-time inference using these small distilled models on next-generation flight hardware such as the High Performance Spaceflight Computer (HPSC). (via Semantic Scholar)
UN Sustainable Development Goal Categories
13. Climate Action (Web of Science)
Source: Web Of Science
Added: September 18, 2023

2023 article

UNSUPERVISED SAR IMAGES FOR SUBMESOSCALE OCEANIC EDDY DETECTION

IGARSS 2023 - 2023 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, pp. 2065–2068.

By: G. Vincent n, K. Pak *, D. Martinez *, E. Goh *, J. Wang  n, B. Bue*, B. Holt*, B. Wilson *

author keywords: Synthetic Aperture Radar; Submesoscale Eddies; Contrastive Learning
TL;DR: This study proposes a novel semi-supervised framework that extracts meaningful features from unlabeled SAR images and fine-tune them using a small set of labeled images using SimCLR and MoCo algorithms, and achieves promising outcomes and superior performance in SAR-based submesoscale eddy detection, surpassing supervised techniques. (via Semantic Scholar)
UN Sustainable Development Goal Categories
14. Life Below Water (OpenAlex)
Source: Web Of Science
Added: March 25, 2024

Citation Index includes data from a number of different sources. If you have questions about the sources of data in the Citation Index or need a set of data which is free to re-distribute, please contact us.

Certain data included herein are derived from the Web of Science© and InCites© (2024) of Clarivate Analytics. All rights reserved. You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.