Automatic discovery of discriminative parts as a quadratic assignment problem
This work addresses the challenge of improving image classification accuracy for researchers and practitioners in computer vision, though it is incremental as it builds on existing part-based methods.
The paper tackles the problem of automatically learning discriminative parts for part-based image classification by formulating it as a quadratic assignment problem, achieving state-of-the-art results on the Willow actions and MIT 67 scenes datasets.
Part-based image classification consists in representing categories by small sets of discriminative parts upon which a representation of the images is built. This paper addresses the question of how to automatically learn such parts from a set of labeled training images. The training of parts is cast as a quadratic assignment problem in which optimal correspondences between image regions and parts are automatically learned. The paper analyses different assignment strategies and thoroughly evaluates them on two public datasets: Willow actions and MIT 67 scenes. State-of-the art results are obtained on these datasets.