BiCoS: A Bi-level Co-Segmentation Method for Image Classification
Y Chai, Victor Lempitsky and Andrew Zisserman
In: ICCV 2011, 6-13 November 2011, Barcelona.
The objective of this paper is the unsupervised segmentation
of image training sets into foreground and background
in order to improve image classification performance. To
this end we introduce a new scalable, alternation-based algorithm for co-segmentation, BiCoS, which is simpler than
many of its predecessors, and yet has superior performance
on standard benchmark image datasets. We argue that the reason for this success is that the cosegmentation
task is represented at the appropriate levels – pixels and color distributions for individual images, and super-pixels with learnable features at the level of sharing across the image set – together with powerful and efficient
inference algorithms (GrabCut and SVM) for each level.
We assess both the segmentation and classification performance of the algorithm and compare to previous results
on Oxford Flowers 17 & 102, Caltech-UCSD Birds-200, the
Weizmann Horses, Caltech-4 benchmark datasets.