Context Matters: Graph-based Self-supervised Representation Learning for Medical Images

Improvements to context based self-supervised learning

We develop a set of methods to improve on the results of self-supervised learning using context. We start with a baseline of patch based arrangement context learning and go from there. Our methods address some overt problems such as chromatic aberration as well as other potential problems such as spatial skew and mid-level feature neglect. We prevent problems with testing generalization on comm...

Graph-based Semi-Supervised Learning Framework for Medical Image Retrieval

As low level features can not reflect the high level semantic in medical image search, in this paper, we propose an image retrieval algorithm to combine visual concept and local features by graph-based semi-supervised learning framework. More specific, we construct a graph model by distance between images, and add density similarity measure in the label propagation progress to get the membershi...

Graph-Based Semi-Supervised Learning

While labeled data is expensive to prepare, ever increasing amounts of unlabeled data is becoming widely available. In order to adapt to this phenomenon, several semi-supervised learning (SSL) algorithms, which learn from labeled as well as unlabeled data, have been developed. In a separate line of work, researchers have started to realize that graphs provide a natural way to represent data in ...

Context Based Covariance for Supervised Learning

This paper proposes a new metric, called Context Based Covariance, to capture contextual information intrinsic to multivariate data. Based on this concept, a minimum distance classifier is designed, and its applicability to the domain of supervised machine learning is discussed. The performance of the proposed metric is compared with conventional minimum distance classifiers based on Mahalanobi...

Hyper-parameter Learning for Graph Based Semi-supervised Learning Algorithms