Compact Bilinear Pooling

• Published in: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp. 317 - 326
• Main Authors: Yang Gao, Beijbom, Oscar, Ning Zhang, Darrell, Trevor
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2016
• Subjects: Convolution; Encoding; Feature extraction; Kernel; Pipelines; Tensile stress; Visualization
• ISSN: 1063-6919
• DOI: 10.1109/CVPR.2016.41

Bilinear models has been shown to achieve impressive performance on a wide range of visual tasks, such as semantic segmentation, fine grained recognition and face recognition. However, bilinear features are high dimensional, typically on the order of hundreds of thousands to a few million, which makes them impractical for subsequent analysis. We propose two compact bilinear representations with the same discriminative power as the full bilinear representation but with only a few thousand dimensions. Our compact representations allow back-propagation of classification errors enabling an end-to-end optimization of the visual recognition system. The compact bilinear representations are derived through a novel kernelized analysis of bilinear pooling which provide insights into the discriminative power of bilinear pooling, and a platform for further research in compact pooling methods. Experimentation illustrate the utility of the proposed representations for image classification and few-shot learning across several datasets.