8 citations · 16 across the 7 of their papers we have counts for
9 papers
Resolving label uncertainty with implicit posterior models
Esther Rolf, Nikolay Malkin, Alexandros Graikos +3
We propose a method for jointly inferring labels across a collection of data samples, where each sample consists of an observation and a prior belief about the label. By implicitly…
Model Generalization in Deep Learning Applications for Land Cover Mapping
Lucas Hu, Caleb Robinson, Bistra Dilkina
Recent work has shown that deep learning models can be used to classify land-use data from geospatial satellite imagery. We show that when these deep learning models are trained on…
Mining self-similarity: Label super-resolution with epitomic representations
Nikolay Malkin, Anthony Ortiz, Caleb Robinson +1
We show that simple patch-based models, such as epitomes, can have superior performance to the current state of the art in semantic segmentation and label super-resolution, which u…
Local Context Normalization: Revisiting Local Normalization
Anthony Ortiz, Caleb Robinson, Dan Morris +4
Normalization layers have been shown to improve convergence in deep neural networks, and even add useful inductive biases. In many vision applications the local spatial context of…
Human-Machine Collaboration for Fast Land Cover Mapping
Caleb Robinson, Anthony Ortiz, Kolya Malkin +5
We propose incorporating human labelers in a model fine-tuning system that provides immediate user feedback. In our framework, human labelers can interactively query model predicti…
Migration patterns under different scenarios of sea level rise
Caleb Robinson, Bistra Dilkina, Juan Moreno-Cruz
We propose a framework to examine future migration patterns of people under different sea level rise scenarios using models of human migration. Specifically, we couple a sea level…