Active visual category learning
MetadataShow full item record
Visual recognition research develops algorithms and representations to autonomously recognize visual entities such as objects, actions, and attributes. The traditional protocol involves manually collecting training image examples, annotating them in specific ways, and then learning models to explain the annotated examples. However, this is a rather limited way to transfer human knowledge to visual recognition systems, particularly considering the immense number of visual concepts that are to be learned. I propose new forms of active learning that facilitate large-scale transfer of human knowledge to visual recognition systems in a cost-effective way. The approach is cost-effective in the sense that the division of labor between the machine learner and the human annotators respects any cues regarding which annotations would be easy (or hard) for either party to provide. The approach is large-scale in that it can deal with a large number of annotation types, multiple human annotators, and huge pools of unlabeled data. In particular, I consider three important aspects of the problem: (1) cost-sensitive multi-level active learning, where the expected informativeness of any candidate image annotation is weighed against the predicted cost of obtaining it in order to choose the best annotation at every iteration. (2) budgeted batch active learning, a novel active learning setting that perfectly suits automatic learning from crowd-sourcing services where there are multiple annotators and each annotation task may vary in difficulty. (3) sub-linear time active learning, where one needs to retrieve those points that are most informative to a classifier in time that is sub-linear in the number of unlabeled examples, i.e., without having to exhaustively scan the entire collection. Using the proposed solutions for each aspect, I then demonstrate a complete end-to-end active learning system for scalable, autonomous, online learning of object detectors. The approach provides state-of-the-art recognition and detection results, while using minimal total manual effort. Overall, my work enables recognition systems that continuously improve their knowledge of the world by learning to ask the right questions of human supervisors.
Showing items related by title, author, creator and subject.
Learning with Markov logic networks : transfer learning, structure learning, and an application to Web query disambiguation Mihalkova, Lilyana Simeonova (2011-03-18)Traditionally, machine learning algorithms assume that training data is provided as a set of independent instances, each of which can be described as a feature vector. In contrast, many domains of interest are inherently ...
Informal learning in the Web 2.0 environment : how Chinese students who are learning English use Web 2.0 tools for informal learning Li, Yiran, active 2013 (2013-08-12)The purpose of this master’s report was to investigate how Chinese students who were learning English used Web 2.0 tools for informal learning and to construct a model of informal learning in the Web 2.0 environment. I ...