CVLGJun 10, 2014

Deep Epitomic Convolutional Neural Networks

arXiv:1406.2732v13 citations
Originality Incremental advance
AI Analysis

This work addresses image classification tasks for computer vision researchers, offering an incremental improvement over existing convolutional neural network architectures.

The paper tackles the problem of improving image recognition performance by introducing epitomic convolution as a new building block for deep neural networks, replacing standard convolution and max-pooling layers, and reports improved recognition on Imagenet and excellent performance on Caltech-101.

Deep convolutional neural networks have recently proven extremely competitive in challenging image recognition tasks. This paper proposes the epitomic convolution as a new building block for deep neural networks. An epitomic convolution layer replaces a pair of consecutive convolution and max-pooling layers found in standard deep convolutional neural networks. The main version of the proposed model uses mini-epitomes in place of filters and computes responses invariant to small translations by epitomic search instead of max-pooling over image positions. The topographic version of the proposed model uses large epitomes to learn filter maps organized in translational topographies. We show that error back-propagation can successfully learn multiple epitomic layers in a supervised fashion. The effectiveness of the proposed method is assessed in image classification tasks on standard benchmarks. Our experiments on Imagenet indicate improved recognition performance compared to standard convolutional neural networks of similar architecture. Our models pre-trained on Imagenet perform excellently on Caltech-101. We also obtain competitive image classification results on the small-image MNIST and CIFAR-10 datasets.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes