Instance classification with prototype selection

  title={Instance classification with prototype selection},
  author={Josip Krapac and Florent Perronnin and Teddy Furon and Herv{\'e} J{\'e}gou},
We address the problem of instance classification: our goal is to annotate images with tags corresponding to objects classes which exhibit small intra-class variations such as logos, products or landmarks. We propose a novel algorithm for the selection of class-specific prototypes which are used in a voting-based classification scheme. We show significant improvements over two state-of-the-art methods, namely the Fisher vector and Hamming Embedding, on two challenging methods of logos and… CONTINUE READING