Here is a short abstract of the thesis: Object detectors are important components in many intelligent systems. They are typically obtained with fully-supervised training which require costly annotated data. This thesis considers annotation-efficient alternatives to fully-supervised object detection. In particular, we discuss several approaches to Unsupervised Object Discovery, which aims to link images containing similar objects and localize these without any supervision. We also introduce a framework which combines active learning and weakly-supervised object detection that demonstrates a better detection performance / annotation cost trade-off than both fully- and weakly-supervised object detection.
Van Huy Vo defended PR[AI]RIE Cifre thesis
On November 28, Huy Vo defended his PhD thesis entitled “Annotation-efficient learning for object discovery and detection". Congratulations!