Simple Techniques Make Sense: Feature Pooling and Normalization for Image Classification

Image classification is a fundamental task in computer vision, implying a wide range of challenging problems, such as object recognition, scene understanding and image tagging. One of the most popular approaches for image classification, the Bag-of-Features (BoF) model, represents an image with a long feature vector, and adopt machine learning algorithms for training and testing. Owing to its simplicity and scalability, the BoF model is widely used in both academic researches and industrial applications. This paper discusses the feature summarization stage, including pooling and normalization, in the BoF model. We show that these two modules, although devalued sometimes, have important impacts on image classification performance. We present two algorithms, i.e., Generalized Regular Spatial Pooling (GRSP) for constructing a better group of spatial bins, and Hierarchical Feature Normalization (HFN) for assigning proper weights for regional feature normalization. Both algorithms are independent of the descriptor extraction and feature encoding stages, therefore they could be transplanted freely onto many other classification frameworks based on local feature statistics. We further provide insightful discussions for the natures of designing efficient image classification models. Experiments verify that the proposed algorithm achieves state-of-the-art results on a wide range of image classification datasets.