Unsupervised Object Class Discovery via Saliency-Guided Multiple Class Learning

Jun-Yan Zhu, Jiajun Wu, Yan Xu, Eric Chang, Zhuowen Tu
2015 IEEE Transactions on Pattern Analysis and Machine Intelligence  
Discovering object classes from images in a fully unsupervised way is an intrinsically ambiguous task; saliency detection approaches however ease the burden on unsupervised learning. We develop an algorithm for simultaneously localizing objects and discovering object classes via bottom-up (saliency-guided) multiple class learning (bMCL), and make the following contributions: (1) saliency detection is adopted to convert unsupervised learning into multiple instance learning, formulated as
more » ... p multiple class learning (bMCL); (2) we utilize the Discriminative EM (DiscEM) to solve our bMCL problem and show DiscEM's connection to the MIL-Boost method[34]; (3) localizing objects, discovering object classes, and training object detectors are performed simultaneously in an integrated framework; (4) significant improvements over the existing methods for multi-class object discovery are observed. In addition, we show single class localization as a special case in our bMCL framework and we also demonstrate the advantage of bMCL over purely data-driven saliency methods.
doi:10.1109/tpami.2014.2353617 pmid:26353299 fatcat:cg3y3ayekvdapd74ijzwpaxruy