Evaluation of Pooling Operations in Convolutional Architectures for Object Recognition

A common practice to gain invariant features in object recognition models is to aggregate multiple low-level features over a small neighborhood. However, the differences between those models makes a comparison of the properties of different aggregation functions hard. Our aim is to gain insight into different functions by directly comparing them on a fixed architecture for several common object recognition tasks. Empirical results show that a maximum pooling operation significantly outperforms subsampling operations. Despite their shift-invariant properties, overlapping pooling windows are no significant improvement over non-overlapping pooling windows. By applying this knowledge, we achieve state-of-the-art error rates of 4.57% on the NORB normalized-uniform dataset and 5.6% on the NORB jittered-cluttered dataset.