We call our framework Active Semi Supervised Learning (ASSL), which outperforms these traditional existing methods.
We also find that the proposed ASSL method can be applied to a number of computer vision applications.
The proposed ASSL method is represent in Algorithm 1.
For person detection, we use the Faster R-CNN  convolutional neural network based on an object detector and an ASSL framework that is implemented on the popular Caffe deep learning library .
Table 2 Shows the results of our proposed method, using the ASSL framework for both simple and complex environments.