activity
20142024
most citedAn Easy to Use Repository for Comparing and Improving Machine Learning Algorithm Usage

9 citations · 23 across the 8 of their papers we have counts for

collaborators

8 papers

cs.CV20241 cited

DELINE8K: A Synthetic Data Pipeline for the Semantic Segmentation of Historical Documents

Taylor Archibald, Tony Martinez

Document semantic segmentation is a promising avenue that can facilitate document analysis tasks, including optical character recognition (OCR), form classification, and document e…

cs.CV2021

Generalizing Interactive Backpropagating Refinement for Dense Prediction

Fanqing Lin, Brian Price, Tony Martinez

As deep neural networks become the state-of-the-art approach in the field of computer vision for dense prediction tasks, many methods have been developed for automatic estimation o…

stat.ML20142 cited

A Hierarchical Multi-Output Nearest Neighbor Model for Multi-Output Dependence Learning

Richard G. Morris, Tony Martinez, Michael R. Smith

Multi-Output Dependence (MOD) learning is a generalization of standard classification problems that allows for multiple outputs that are dependent on each other. A primary issue th…

cs.LG20148 cited

Recommending Learning Algorithms and Their Associated Hyperparameters

Michael R. Smith, Logan Mitchell, Christophe Giraud-Carrier +1

The success of machine learning on a given task dependson, among other things, which learning algorithm is selected and its associated hyperparameters. Selecting an appropriate lea…

stat.ML20149 cited

An Easy to Use Repository for Comparing and Improving Machine Learning Algorithm Usage

Michael R. Smith, Andrew White, Christophe Giraud-Carrier +1

The results from most machine learning experiments are used for a specific purpose and then discarded. This results in a significant loss of information and requires rerunning expe…

stat.ML2014

Reducing the Effects of Detrimental Instances

Michael R. Smith, Tony Martinez

Not all instances in a data set are equally beneficial for inducing a model of the data. Some instances (such as outliers or noise) can be detrimental. However, at least initially,…