Learning and Visualizing the Construction of Visual Features from Image Data – Most of the existing methods use a linear classifier for image classification. In this paper, we present a new approach for image classification by maximizing the expected class error rate of the linear classifier when a linear classifier is used for classifying images using a set of labeled images. We propose a robust classifier that achieves this expected regret by incorporating a set of labeled images into the training set, such that for a certain class, the image classification fails. Our method is guaranteed to yield a linear regret for the output data even for class labels that are noisy. We empirically validate our method, demonstrate that the method consistently achieves a linear regret for the input images, and show that our method achieves better classification performance.
Object segmentation has been extensively used as a tool to train human-machine interfaces to recognize objects and identify them in video. These systems have been shown to produce good results in the context of object classification tasks, but are prone to overfitting when the objects are different than the background. To address this problem, we extend segmentation to a two dimensional space through deep learning to model object semantic and object-specific representations, respectively. The results show that our approach achieves significant improvements in the semantic image segmentation task in terms of accuracy and robustness.
Learning from non-deterministic examples
A Semantics-Driven Approach to Evaluation of Sports Teams’ Ratings from Draft Descriptions
Learning and Visualizing the Construction of Visual Features from Image Data
A Unified Approach to Evaluating the Fitness of Classifiers
DenseNet: Generating Multi-Level Neural Networks from End-to-End Instructional VideosObject segmentation has been extensively used as a tool to train human-machine interfaces to recognize objects and identify them in video. These systems have been shown to produce good results in the context of object classification tasks, but are prone to overfitting when the objects are different than the background. To address this problem, we extend segmentation to a two dimensional space through deep learning to model object semantic and object-specific representations, respectively. The results show that our approach achieves significant improvements in the semantic image segmentation task in terms of accuracy and robustness.