Hello! I'm Isaac Corley

I’m currently a PhD candidate in the SAIL lab at the University of Texas at San Antonio (UTSA) advised by Paul Rad (Peyman Najafirad). My research is focused on 3D and Multimodal Computer Vision in Remote Sensing (satellite and aerial imagery).

I’m excited about open-source software and currently maintain the TorchGeo and TorchSeg libraries.

I’ve worked as a full-time and contract ML Engineer for several years at various companies where I’ve mainly applied computer vision methods to drone, aerial, and satellite imagery. In previous years I was heavily involved in machine learning applications of signal processing, cybersecurity, and biomedical sensors.

CV Scholar Github Twitter

News

Publications

A Change Detection Reality Check

A Change Detection Reality Check

Isaac Corley, Caleb Robinson, Anthony Ortiz
ICLR 2024 Machine Learning for Remote Sensing (ML4RS) Workshop

We present an analysis of the current state-of-the-art in change detection literature. We find that a simple baseline of U-Net, an architecture from 2015, is still a top performer on several benchmarks and consistently outperforms many recently proposed methods.

Project Page PDF arXiv Code
Seeing the roads through the trees: A benchmark for modeling spatial dependencies with aerial imagery

Seeing the roads through the trees: A benchmark for modeling spatial dependencies with aerial imagery

Caleb Robinson, Isaac Corley, Anthony Ortiz, Rahul Dodhia, Juan Lavista Ferres, Peyman Najafirad
ArXiv 2024

We introduce a novel remote sensing dataset for evaluating a model's ability to learn long-range spatial dependencies in aerial imagery by performing road extraction while containing large gaps occluded by tree canopy.

Project Page PDF arXiv Code
ZRG: A Dataset for Multimodal 3D Residential Rooftop Understanding

ZRG: A Dataset for Multimodal 3D Residential Rooftop Understanding

Isaac Corley, Jonathan Lwowski, Peyman Najafirad
WACV 2024

We present a novel dataset for 3D understanding of roofs containing imagery, digital surface models, and 3D roof geometries captured from over 20k residential inspections.

Project Page PDF arXiv Code
Revisiting pre-trained remote sensing model benchmarks: resizing and normalization matters

Revisiting pre-trained remote sensing model benchmarks: resizing and normalization matters

Isaac Corley, Caleb Robinson, Rahul Dodhia, Juan Lavista Ferres, Peyman Najafirad
ArXiv 2023

We perform a fair and large-scale evaluation of remote sensing foundation models and find chip/tile size and normalization preprocessing to be paramount for achieving peak performance for each individual pretrained model.

Project Page PDF arXiv Code
SSL4EO-L: Datasets and Foundation Models for Landsat Imagery

SSL4EO-L: Datasets and Foundation Models for Landsat Imagery

Adam Stewart, Nils Lehmann, Isaac Corley, Yi Wang, Yi-Chia Chang, Nassim Ait Ali Braham, Shradha Sehgal, Caleb Robinson, Arindam Banerjee
NeurIPS 2023

We introduce SSL4EO-L, the first ever dataset designed for self-supervised learning for Earth Observation for the Landsat family of satellites.

Project Page PDF arXiv Code
Solar Panel Mapping via Oriented Object Detection

Solar Panel Mapping via Oriented Object Detection

Conor Wallace, Isaac Corley, Jonathan Lwowski
ICLR 2023 Tackling Climate Change with Machine Learning Workshop

We detail Zeitview's deployed end-to-end deep learning framework for detecting solar panels using rotated object detection architectures in large scale solar farms.

Project Page PDF arXiv
TorchGeo: Deep Learning with Geospatial Data

TorchGeo: Deep Learning with Geospatial Data

Adam Stewart, Caleb Robinson, Isaac Corley, Anthony Ortiz, Juan Lavista Ferres, Arindam Banerjee
ACM SIGSPATIAL 2023

We introduce TorchGeo, a Python library for integrating geospatial data into the PyTorch deep learning ecosystem.

Project Page PDF arXiv Code
Supervising Remote Sensing Change Detection Models with 3D Surface Semantics

Supervising Remote Sensing Change Detection Models with 3D Surface Semantics

Isaac Corley, Peyman Najafirad
ICIP 2022

We propose Contrastive Surface-Image Pretraining (CSIP) for joint learning a latent space which extracts surface level features from optical RGB imagery which we show improves the performance in surface relevant tasks e.g. building segmentation and change detection.

Project Page PDF arXiv Code
Self-Supervised Representation Learning Enhances Broad Area Search in Multi-Temporal Satellite Imagery

Self-Supervised Representation Learning Enhances Broad Area Search in Multi-Temporal Satellite Imagery

Thomas Stephens, Isaac Corley, Adrian Gould, Anthony Polakiewicz
IGARSS 2022

We propose pretraining on satellite image time-series (SITS) using the Contrastive Predictive Coding (CPC) self-supervised learning method which dramatically improves the performance of Broad Area Search (BAS) tasks in limited labeled data settings.

Project Page PDF arXiv
Destruction of Image Steganography using Generative Adversarial Networks

Destruction of Image Steganography using Generative Adversarial Networks

Isaac Corley, Jonathan Lwowski, Justin Hoffman
ArXiv 2019

We propose a Generative Adversarial Network (GAN) based method we coin Deep Digital Steganography Purifier (DDSP), which is optimized to remove steganographic content embedded in image pixels without compromising the perceptual quality of the original image.

Project Page PDF arXiv
DomainGAN: Generating Adversarial Examples to Attack Domain Generation Algorithm Classifiers

DomainGAN: Generating Adversarial Examples to Attack Domain Generation Algorithm Classifiers

Isaac Corley, Jonathan Lwowski, Justin Hoffman
ArXiv 2019

We propose DomainGAN which generates adversarial domains with near identical characteristics to benign domains and which greatly evades SOTA DGA classifiers.

Project Page PDF arXiv
Deep EEG Super-Resolution: Upsampling EEG Spatial Resolution with Generative Adversarial Networks

Deep EEG Super-Resolution: Upsampling EEG Spatial Resolution with Generative Adversarial Networks

Isaac Corley, Yufei Huang
IEEE Biomedical & Health Informatics (BHI) 2019

We train a Generative Adversarial Network (GAN) to upsample the spatial resolution of EEG datasets by generating realistic signals, eliminating the need for expensive EEG hardware.

Project Page PDF arXiv