Compact Bilinear Pooling
Yang Gao, Oscar Beijbom, Ning Zhang, Trevor Darrell
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/gy20073/compact_bilinear_poolingOfficialIn papertf★ 0
- github.com/Seth-Park/MultimodalExplanationscaffe2★ 0
- github.com/akirafukui/vqa-mcbcaffe2★ 0
- github.com/aniket03/keras_compact_bilnear_CNNtf★ 0
- github.com/jnhwkim/cbptorch★ 0
- github.com/divelab/vqa-textcaffe2★ 0
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.