Abstract
Generic human detectors perform poorly in application scenes in which conditions are significantly different from those of the benchmark data sets. Based on the assumption that only a limited number of labeled examples are available, we propose a variant semi-supervised boosting approach for improving scene adaptiveness by utilizing unlabeled data. Specifically, we train a max-margin-based model as an initial detector for new example collection, instead of using generic detectors, and then a better model is trained via boosting in which the newly obtained examples influence the training process through their similarities to the labeled examples. Since the widely used human descriptors are usually high dimensional and redundant, we employ a graph-based method to determine the weight representing the importance of each feature, such that the weighted similarity measurement leads to a performance gain. In the experiments, the effectiveness of the proposed approach “Variant SemiBoost” is demonstrated and state-of-the-art performance on challenging data sets is achieved.
Funding Information
  • National Natural Science Foundation of China (61502173)
  • Natural Science Foundation of Guangdong Province (2016A030310422)
  • Fundamental Research Funds for the Central Universities (2015ZM077)
  • National Undergraduate Innovative and Entrepreneurial Training Program (201610561124)
  • Research Grants Council of the Hong Kong Special Administration Region (CityU 11300715)
  • City University of Hong Kong (7004674)

This publication has 48 references indexed in Scilit: