Learning relative features through adaptive pooling for image classification

Publisher:
IEEE
Publication Type:
Conference Proceeding
Citation:
Proceedings - IEEE International Conference on Multimedia and Expo, 2014, (Septmber)
Issue Date:
2014-09-03
Full metadata record
Files in This Item:
Filename Description Size
OCC-107388_AM.pdfAccepted Manuscript version1.25 MB
Adobe PDF
© 2014 IEEE. Bag-of-Feature (BoF) representations and spatial constraints have been popular in image classification research. One of the most successful methods uses sparse coding and spatial pooling to build discriminative features. However, minimizing the reconstruction error by sparse coding only considers the similarity between the input and codebooks. In contrast, this paper describes a novel feature learning approach for image classification by considering the dissimilarity between inputs and prototype images, or what we called reference basis (RB). First, we learn the feature representation by max-margin criterion between the input and the RB. The learned hyperplane is stored as the relative feature. Second, we propose an adaptive pooling technique to assemble multiple relative features generated by different RBs under the SVM framework, where the classifier and the pooling weights are jointly learned. Experiments based on three challenging datasets: Caltech-101, Scene 15 and Willow-Actions, demonstrate the effectiveness and generality of our framework.
Please use this identifier to cite or link to this item: