Timezone: »

 
Poster
Learning Deep Bilinear Transformation for Fine-grained Image Representation
Heliang Zheng · Jianlong Fu · Zheng-Jun Zha · Jiebo Luo

Thu Dec 12 05:00 PM -- 07:00 PM (PST) @ East Exhibition Hall B + C #149
in Applications -- Object Recognition »

Bilinear feature transformation has shown the state-of-the-art performance in learning fine-grained image representations. However, the computational cost to learn pairwise interactions between deep feature channels is prohibitively expensive, which restricts this powerful transformation to be used in deep neural networks. In this paper, we propose a deep bilinear transformation (DBT) block, which can be deeply stacked in convolutional neural networks to learn fine-grained image representations. The DBT block can uniformly divide input channels into several semantic groups. As bilinear transformation can be represented by calculating pairwise interactions within each group, the computational cost can be heavily relieved. The output of each block is further obtained by aggregating intra-group bilinear features, with residuals from the entire input features. We found that the proposed network achieves new state-of-the-art in several fine-grained image recognition benchmarks, including CUB-Bird, Stanford-Car, and FGVC-Aircraft.

Keywords: Object Recognition · CNN Architectures · Applications · Deep Learning

Author Information

Heliang Zheng (University of Science and Technology of China)
Jianlong Fu (Microsoft Research)
Zheng-Jun Zha (University of Science and Technology of China)
Jiebo Luo (U. Rochester)

More from the Same Authors