Adaptive Learning for Segmentation and Detection
Jingjing Deng · 2017
Segmentation and detection are two fundamental problems in computer vision and medical image analysis, they are intrinsically interlinked by the nature of machine learning based classification, especially supervised learning methods. Many automatic segmentation methods have been proposed which heavily rely on hand-crafted discriminative features for specific geometry and powerful classifier for delinearating the foreground object and background region. The aim of this thesis is to investigate the adaptive schemes that can be used to derive efficient interactive segmentation methods for medical imaging applications, and adaptive detection methods for addressing generic computer vision problems. In this thesis, we consider adaptive learning as a progressive learning process that gradually builds the model given sequential supervision from user interactions. The learning process could be either adaptive re-training for small scale models and datasets or adaptive fine-tuning for medium-large scale. In addition, adaptive learning is considered as a progressive learning process that gradually subdivides a big and dif-Throughout the time of Doctor of Philosophy studying, I had the luck to experience the guidance, mentoring, friendship, assistance, criticism and love of many great people. It is their commitment that brought me in the position of being able to carry out scientific research and finish this thesis.