David Kriegman
YOU?
Author Swipe
View article: Quantifying coral reef carbonate budgets: a comparison between ReefBudget and CoralNet
Quantifying coral reef carbonate budgets: a comparison between ReefBudget and CoralNet Open
Calcium carbonate production constitutes one of the core processes that drive coral reef ecosystem functioning and can be assessed using in-water or image-based survey methods, which have not previously been compared. This study compares c…
View article: Quantifying coral reef carbonate budgets: a comparison between ReefBudget and CoralNet
Quantifying coral reef carbonate budgets: a comparison between ReefBudget and CoralNet Open
Calcium carbonate production constitutes one of the core processes that drive coral reef ecosystem functioning and can be assessed using in-water or image-based survey methods, which have not previously been compared. This study compares c…
View article: One-Vote Veto: Semi-Supervised Learning for Low-Shot Glaucoma Diagnosis
One-Vote Veto: Semi-Supervised Learning for Low-Shot Glaucoma Diagnosis Open
Convolutional neural networks (CNNs) are a promising technique for automated glaucoma diagnosis from images of the fundus, and these images are routinely acquired as part of an ophthalmic exam. Nevertheless, CNNs typically require a large …
View article: Rapid assessments of Pacific Ocean net coral reef carbonate budgets and net calcification following the 2014–2017 global coral bleaching event
Rapid assessments of Pacific Ocean net coral reef carbonate budgets and net calcification following the 2014–2017 global coral bleaching event Open
The 2014–2017 global coral bleaching event caused widespread coral mortality; however, its impact on the capacity for coral reefs to maintain calcium carbonate structures has not been determined. Here, we quantified remotely sensed maximum…
View article: Detecting Glaucoma from Fundus Photographs Using Deep Learning without Convolutions: Transformer for Improved Generalization
Detecting Glaucoma from Fundus Photographs Using Deep Learning without Convolutions: Transformer for Improved Generalization Open
Purpose: To compare the diagnostic accuracy and explainability of a new Vision Transformer deep learning technique, Data-efficient image Transformer (DeiT), and Resnet-50, trained on fundus photographs from the Ocular Hypertension Treatm…
View article: Detecting Glaucoma from Fundus Photographs Using Deep Learning without Convolutions: Transformer for Improved Generalization
Detecting Glaucoma from Fundus Photographs Using Deep Learning without Convolutions: Transformer for Improved Generalization Open
Purpose: To compare the diagnostic accuracy and explainability of a new Vision Transformer deep learning technique, Data-efficient image Transformer (DeiT), and Resnet-50, trained on fundus photographs from the Ocular Hypertension Treatm…
View article: Detecting Glaucoma in the Ocular Hypertension Study Using Deep Learning
Detecting Glaucoma in the Ocular Hypertension Study Using Deep Learning Open
To investigate the diagnostic accuracy of deep learning (DL) algorithms to detect primary open-angle glaucoma (POAG) trained on fundus photographs from the Ocular Hypertension Treatment Study (OHTS). 66,715 photographs from 3,272 eyes were…
View article: Detecting Glaucoma in the Ocular Hypertension Treatment Study Using Deep Learning: Implications for clinical trial endpoints
Detecting Glaucoma in the Ocular Hypertension Treatment Study Using Deep Learning: Implications for clinical trial endpoints Open
To investigate the diagnostic accuracy of deep learning (DL) algorithms to detect primary open-angle glaucoma (POAG) trained on fundus photographs from the Ocular Hypertension Treatment Study (OHTS). 66,715 photographs from 3,272 eyes were…
View article: Area-normalized scaling of ReefBudget calcification, macrobioerosion, and microbioerosion rates for use with CoralNet Version 1.0
Area-normalized scaling of ReefBudget calcification, macrobioerosion, and microbioerosion rates for use with CoralNet Version 1.0 Open
The following code generates area-normalized calcification, macrobioerosion, and microbioerosion rates from ReefBudget methodologies (http://geography.exeter.ac.uk/reefbudget/; Perry et al., 2018; Perry and Lange 2019) for use with CoralNe…
View article: Detecting Glaucoma in the Ocular Hypertension Study Using Deep Learning
Detecting Glaucoma in the Ocular Hypertension Study Using Deep Learning Open
To investigate the diagnostic accuracy of deep learning (DL) algorithms to detect primary open-angle glaucoma (POAG) trained on fundus photographs from the Ocular Hypertension Treatment Study (OHTS). 66,715 photographs from 3,272 eyes were…
View article: Detecting Glaucoma in the Ocular Hypertension Treatment Study Using Deep Learning: Implications for clinical trial endpoints
Detecting Glaucoma in the Ocular Hypertension Treatment Study Using Deep Learning: Implications for clinical trial endpoints Open
To investigate the diagnostic accuracy of deep learning (DL) algorithms to detect primary open-angle glaucoma (POAG) trained on fundus photographs from the Ocular Hypertension Treatment Study (OHTS). 66,715 photographs from 3,272 eyes were…
View article: The Coral Reef Sentinels Program: A Mars Shot for Blue Planetary Health
The Coral Reef Sentinels Program: A Mars Shot for Blue Planetary Health Open
Up to 90% of global coral reefs are predicted to be severely degraded by 2050 under “business-as-usual” scenarios. To meet the scale and scope of this challenge, we propose designing and demonstrating a multi-modal system that can incorpor…
View article: One-Vote Veto: Semi-Supervised Learning for Low-Shot Glaucoma Diagnosis
One-Vote Veto: Semi-Supervised Learning for Low-Shot Glaucoma Diagnosis Open
Convolutional neural networks (CNNs) are a promising technique for automated glaucoma diagnosis from images of the fundus, and these images are routinely acquired as part of an ophthalmic exam. Nevertheless, CNNs typically require a large …
View article: Neural Reflectance Fields for Appearance Acquisition
Neural Reflectance Fields for Appearance Acquisition Open
We present Neural Reflectance Fields, a novel deep scene representation that encodes volume density, normal and reflectance properties at any 3D point in a scene using a fully-connected neural network. We combine this representation with a…
View article: Deep 3D Capture: Geometry and Reflectance From Sparse Multi-View Images
Deep 3D Capture: Geometry and Reflectance From Sparse Multi-View Images Open
We introduce a novel learning-based method to reconstruct the high-quality geometry and complex, spatially-varying BRDF of an arbitrary object from a sparse set of only six images captured by wide-baseline cameras under collocated point li…
View article: Detecting the Starting Frame of Actions in Video
Detecting the Starting Frame of Actions in Video Open
In this work, we address the problem of precisely localizing key frames of an action, for example, the precise time that a pitcher releases a baseball, or the precise time that a crowd begins to applaud. Key frame localization is a largely…
View article: Enforcing Reasoning in Visual Commonsense Reasoning
Enforcing Reasoning in Visual Commonsense Reasoning Open
The task of Visual Commonsense Reasoning is extremely challenging in the sense that the model has to not only be able to answer a question given an image, but also be able to learn to reason. The baselines introduced in this task are quite…
View article: Image to Image Translation for Domain Adaptation
Image to Image Translation for Domain Adaptation Open
We propose a general framework for unsupervised domain adaptation, which allows deep neural networks trained on a source domain to be tested on a different target domain without requiring any training annotations in the target domain. This…
View article: Caribbean massive corals not recovering from repeated thermal stress events during 2005–2013
Caribbean massive corals not recovering from repeated thermal stress events during 2005–2013 Open
Massive coral bleaching events associated with high sea surface temperatures are forecast to become more frequent and severe in the future due to climate change. Monitoring colony recovery from bleaching disturbances over multiyear time fr…
View article: Dense Volume-to-Volume Vascular Boundary Detection
Dense Volume-to-Volume Vascular Boundary Detection Open
In this work, we present a novel 3D-Convolutional Neural Network (CNN) architecture called I2I-3D that predicts boundary location in volumetric data. Our fine-to-fine, deeply supervised framework addresses three critical issues to 3D bound…
View article: Improving Automated Annotation of Benthic Survey Images Using Wide-band Fluorescence
Improving Automated Annotation of Benthic Survey Images Using Wide-band Fluorescence Open
Large-scale imaging techniques are used increasingly for ecological surveys. However, manual analysis can be prohibitively expensive, creating a bottleneck between collected images and desired data-products. This bottleneck is particularly…
View article: Learning Concept Embeddings with Combined Human-Machine Expertise
Learning Concept Embeddings with Combined Human-Machine Expertise Open
This paper presents our work on "SNaCK," a low-dimensional concept embedding algorithm that combines human expertise with automatic machine similarity kernels. Both parts are complimentary: human insight can capture relationships that are …
View article: Towards Automated Annotation of Benthic Survey Images: Variability of Human Experts and Operational Modes of Automation
Towards Automated Annotation of Benthic Survey Images: Variability of Human Experts and Operational Modes of Automation Open
Global climate change and other anthropogenic stressors have heightened the need to rapidly characterize ecological changes in marine benthic communities across large scales. Digital photography enables rapid collection of survey images to…