• Publications
  • Influence
Multiple kernels for object detection
TLDR
This work uses multiple kernel learning of Varma and Ray (ICCV 2007) to learn an optimal combination of exponential χ2 kernels, each of which captures a different feature channel.
Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs.
TLDR
An algorithm based on deep machine learning had high sensitivity and specificity for detecting referable diabetic retinopathy and diabetic macular edema in retinal fundus photographs from adults with diabetes.
Geodesic star convexity for interactive image segmentation
TLDR
A new shape constraint for interactive image segmentation is introduced, an extension of Veksler's star-convexity prior, in two ways: from a single star to multiple stars and from Euclidean rays to Geodesic paths.
Who Said What: Modeling Individual Labelers Improves Classification
TLDR
This work proposes modeling the experts individually and then learning averaging weights for combining them, possibly in sample-specific ways to give more weight to more reliable experts and take advantage of the unique strengths of individual experts at classifying certain types of data.
Grader variability and the importance of reference standards for evaluating machine learning models for diabetic retinopathy
TLDR
Adjudication reduces the errors in DR grading by using a small number of adjudicated consensus grades as a tuning dataset and higher-resolution images as input, and to train an improved automated algorithm for DR grading.
Humanising GrabCut: Learning to segment humans using the Kinect
TLDR
It is shown that a large dataset of roughly 3400 humans can be automatically acquired very cheaply using the Kinect, and that the method can be completely automated - segmenting humans given only the images, without requiring a bounding box, and compared with a previous state of the art method.
Performance of a Deep-Learning Algorithm vs Manual Grading for Detecting Diabetic Retinopathy in India.
TLDR
This study shows that the automated DR system generalizes to this population of Indian patients in a prospective setting and demonstrates the feasibility of using an automated DR grading system to expand screening programs.
Inundation Modeling in Data Scarce Regions
TLDR
An operational system providing flood extent forecast maps covering several flood-prone regions in India is described, with the goal of being sufficiently scalable and cost-efficient to facilitate the establishment of effective flood forecasting systems globally.
Appreciation to IJCV Reviewers
TLDR
The candidates for the 2016 Rio Olympics have been announced and the field is preparing for the Games that will take place in Rio de Janeiro over the course of the summer of 2016.
...
1
2
...