# Deep Spatial Pyramid: The Devil is Once Again in the Details Source: [Deep Spatial Pyramid: The Devil is Once Again in the Details]() Collection index: [llms.txt]() Data updated: 2025-10-27T05:49:55.019Z Authors: Bin-Bin Gao, Xiu-Shen Wei, Jianxin Wu, Weiyao Lin Published: 2015-04-21T02:13:44.000Z ## Abstract 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%). ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()