Empowering Visual Categorization With the GPU

By K. V. D. Sande, Theo Gevers, Cees G. M. Snoek. 2011

109 citations recorded by the source corpus.

Visual categorization is important to manage large collections of digital images and video, where textual metadata is often incomplete or simply unavailable. The bag-of-words model has become the most powerful method for visual categorization of images and video. Despite its high accuracy, a severe drawback of this model is its high computational cost. As the trend to increase computational power in newer CPU and GPU architectures is to increase their level of parallelism, exploiting this parallelism becomes an important direction to handle the computational cost of the bag-of-words approach. When optimizing a system based on the bag-of-words approach, the goal is to minimize the time it takes to process batches of images. this paper, we analyze the bag-of-words model for visual categorization in terms of computational cost and identify two major bottlenecks: the quantization step and the classification step. We address these two bottlenecks by proposing two efficient algorithms for quantization and classification by exploiting the GPU hardware and the CUDA parallel programming model. The algorithms are designed to (1) keep categorization accuracy intact, (2) decompose the problem, and (3) give the same numerical results. In the experiments on large scale datasets, it is shown that, by using a parallel implementation on the Geforce GTX260 GPU, classifying unseen images is 4.8 times faster than a quad-core CPU version on the Core i7 920, while giving the exact same numerical results. In addition, we show how the algorithms can be generalized to other applications, such as text retrieval and video retrieval. Moreover, when the obtained speedup is used to process extra video frames in a video retrieval benchmark, the accuracy of visual categorization is improved by 29%.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

ImageNet Large Scale Visual Recognition Challenge (2014, methodology): “…by dense sampling and vector quantization of several color SIFT features (van de Sande et al., 2010), pooling with spatial pyramid matching (Lazebnik et al., 2006), and classifying with a histogram intersection kernel SVM (Maji and Malik, 2009) trained on a GPU (van de Sande et al., 2011a).”
Predicting Actions from Static Scenes (2014, methodology): “In the rest of this section we use the format <descriptor> <encoding technique> to denote image representation techniques, e.g. CSIFT FV as Fisher Vector encoding for CSIFT descriptors.”
Selective Search for Object Recognition (2013, unknown): “The final round of SVM learning takes around 8 hours per class on a GPU for approximately 30,000 training examples [33] resulting from two rounds of mining negatives on Pascal VOC 2010.”
Do deep features generalize from everyday objects to remote sensing and aerial scenes domains? (2015, background): “For all the other descriptors, images were kept in the original resolution of 64×64 pixels.”