This paper studies the effects of training data on binary text classification and postulates that negative training data is not needed and may even be harmful for the task. Tradit...
The bounding box representation employed by many popular object detection models [3, 6] implicitly assumes all pixels inside the box belong to the object. This assumption makes th...
We present a comprehensive suite of experimentation on the subject of learning from imbalanced data. When classes are imbalanced, many learning algorithms can suffer from the pers...
Jason Van Hulse, Taghi M. Khoshgoftaar, Amri Napol...
The required amount of labeled training data for object detection and classification is a major drawback of current methods. Combining labeled and unlabeled data via semisupervise...
This paper proposes a novel approach to discover a set of class specific "composite features" as the feature pool for the detection and classification of complex objects...
Feng Han, Ying Shan, Harpreet S. Sawhney, Rakesh K...