Statistically Motivated Second Order Pooling
arXiv:1801.07492
Abstract
Second-order pooling, a.k.a.~bilinear pooling, has proven effective for deep learning based visual recognition. However, the resulting second-order networks yield a final representation that is orders of magnitude larger than that of standard, first-order ones, making them memory-intensive and cumbersome to deploy. Here, we introduce a general, parametric compression strategy that can produce more compact representations than existing compression techniques, yet outperform both compressed and uncompressed second-order models. Our approach is motivated by a statistical analysis of the network's activations, relying on operations that lead to a Gaussian-distributed final representation, as inherently used by first-order deep networks. As evidenced by our experiments, this lets us outperform the state-of-the-art first-order and second-order models on several benchmark recognition datasets.
Accepted to ECCV 2018. Camera ready version. 14 page, 5 figures, 3 tables
References in corpus (6)
- Deep Residual Learning for Image Recognition
- Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks
- Rethinking the Inception Architecture for Computer Vision
- Is Second-order Information Helpful for Large-scale Visual Recognition?
- Improved Bilinear Pooling with CNNs
- Material Recognition in the Wild with the Materials in Context Database