Year: 2016
Type: conference-paper
Abstract: 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.
DOI: 10.1109/cvpr.2016.41
Authors: Yang Gao, Oscar Beijbom, Ning Zhang, Trevor Darrell
Institutions: University of California, Berkeley, Snap (United States)
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Awards: G1261808637, NRI: Collaborative Research: Shall I Touch This?: Navigating the Look and Feel of Complex Surfaces, RI: Large: Collaborative Research: Reconstructive recognition: Uniting statistical scene understanding and physics-based visual reasoning, AitF: FULL: Collaborative Research: PEARL: Perceptual Adaptive Representation Learning in the Wild, G6843723984
OpenAlex ID: W2963066927