Deep Spatial Pyramid: The Devil is Once Again in the Details
This work addresses image classification accuracy for computer vision applications, but it is incremental as it focuses on refining existing methods rather than introducing a new paradigm.
The paper tackled image classification by optimizing detailed factors in a deep learning framework, achieving a simple and efficient system with improved accuracy, such as 59.78% on SUN397 compared to the previous state-of-the-art of 53.86%.
In this paper we show that by carefully making good choices for various detailed but important factors in a visual recognition framework using deep learning features, one can achieve a simple, efficient, yet highly accurate image classification system. We first list 5 important factors, based on both existing researches and ideas proposed in this paper. These important detailed factors include: 1) $\ell_2$ matrix normalization is more effective than unnormalized or $\ell_2$ vector normalization, 2) the proposed natural deep spatial pyramid is very effective, and 3) a very small $K$ in Fisher Vectors surprisingly achieves higher accuracy than normally used large $K$ values. Along with other choices (convolutional activations and multiple scales), the proposed DSP framework is not only intuitive and efficient, but also achieves excellent classification accuracy on many benchmark datasets. For example, DSP's accuracy on SUN397 is 59.78%, significantly higher than previous state-of-the-art (53.86%).