Abstract
This paper aims for generic instance search from one example where the instance can be an arbitrary 3D object like shoes, not just near-planar and one-sided instances like buildings and logos. Firstly, we evaluate state-of-the-art instance search methods on this problem. We observe that what works for buildings loses its generality on shoes. Secondly, we propose to use automatically learned categoryspecifific attributes to address the large appearance variations present in generic instance search. On the problem of searching among instances from the same category as the query, the category-specifific attributes outperform existing approaches by a large margin. On a shoe dataset containing 6624 shoe images recorded from all viewing angles, we improve the performance from 36.73 to 56.56 using category-specifific attributes. Thirdly, we extend our methods to search objects without restricting to the specififically known category. We show the combination of category-level information and the category-specifific attributes is superior to combining category-level information with low-level features such as Fisher vector