Mid-level Deep Pattern Mining
This work addresses the need for more efficient and accurate visual element discovery in computer vision, though it appears incremental as it combines existing techniques (CNNs and pattern mining).
The paper tackled the problem of mid-level visual element discovery by integrating Convolutional Neural Networks (CNNs) with pattern mining, resulting in performance that outperforms previous works by a sizeable margin with fewer elements and matches or beats recent CNN-based methods.
Mid-level visual element discovery aims to find clusters of image patches that are both representative and discriminative. In this work, we study this problem from the prospective of pattern mining while relying on the recently popularized Convolutional Neural Networks (CNNs). Specifically, we find that for an image patch, activations extracted from the first fully-connected layer of CNNs have two appealing properties which enable its seamless integration with pattern mining. Patterns are then discovered from a large number of CNN activations of image patches through the well-known association rule mining. When we retrieve and visualize image patches with the same pattern, surprisingly, they are not only visually similar but also semantically consistent. We apply our approach to scene and object classification tasks, and demonstrate that our approach outperforms all previous works on mid-level visual element discovery by a sizeable margin with far fewer elements being used. Our approach also outperforms or matches recent works using CNN for these tasks. Source code of the complete system is available online.