A Taught-Obesrve-Ask (TOA) Method for Object Detection with Critical Supervision
This addresses the labeling efficiency problem for computer vision researchers and practitioners, representing a novel method for a known bottleneck rather than incremental.
The paper tackles the problem of reducing labeling time for object detection by proposing a critically supervised learning methodology called Taught-Observe-Ask (TOA), which achieves significantly improved performance over weakly supervised methods while requiring only about 3-6% of the labeling time of fully supervised approaches.
Being inspired by child's learning experience - taught first and followed by observation and questioning, we investigate a critically supervised learning methodology for object detection in this work. Specifically, we propose a taught-observe-ask (TOA) method that consists of several novel components such as negative object proposal, critical example mining, and machine-guided question-answer (QA) labeling. To consider labeling time and performance jointly, new evaluation methods are developed to compare the performance of the TOA method, with the fully and weakly supervised learning methods. Extensive experiments are conducted on the PASCAL VOC and the Caltech benchmark datasets. The TOA method provides significantly improved performance of weakly supervision yet demands only about 3-6% of labeling time of full supervision. The effectiveness of each novel component is also analyzed.