“…Aiming at improving the existing models by incrementally selecting and annotating the most informative unlabeled samples, Active Learning (AL) has been well studied in the past few decades [3], [4], [5], [6], [7], [8], [9], [10], [11], [12], and applied to various kind of vision tasks, such as image/video categorization [13], [14], [15], [16], [17], text/web classification [18], [19], [20], image/video retrieval [21], [22], etc. In the AL methods [3], [4], [5], classifier/model is first initialized with a relatively small set of labeled training samples.…”