A comparison of dense region detectors for image search and fine-grained classification

29 Oct 2014  ·  Ahmet Iscen, Giorgos Tolias, Philippe-Henri Gosselin, Hervé Jégou ·

We consider a pipeline for image classification or search based on coding approaches like Bag of Words or Fisher vectors. In this context, the most common approach is to extract the image patches regularly in a dense manner on several scales. This paper proposes and evaluates alternative choices to extract patches densely. Beyond simple strategies derived from regular interest region detectors, we propose approaches based on super-pixels, edges, and a bank of Zernike filters used as detectors. The different approaches are evaluated on recent image retrieval and fine-grain classification benchmarks. Our results show that the regular dense detector is outperformed by other methods in most situations, leading us to improve the state of the art in comparable setups on standard retrieval and fined-grain benchmarks. As a byproduct of our study, we show that existing methods for blob and super-pixel extraction achieve high accuracy if the patches are extracted along the edges and not around the detected regions.

PDF Abstract

Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.


No methods listed for this paper. Add relevant methods here