Fast, Accurate Detection of 100,000 Object Classes on a Single Machine
- 1 June 2013
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1814-1821
- https://doi.org/10.1109/cvpr.2013.237
Abstract
Many object detection systems are constrained by the time required to convolve a target image with a bank of filters that code for different aspects of an object's appearance, such as the presence of component parts. We exploit locality-sensitive hashing to replace the dot-product kernel operator in the convolution with a fixed number of hash-table probes that effectively sample all of the filter responses in time independent of the size of the filter bank. To show the effectiveness of the technique, we apply it to evaluate 100,000 deformable-part models requiring over a million (part) filters on multiple scales of a target image in less than 20 seconds using a single multi-core processor with 20GB of RAM. This represents a speed-up of approximately 20,000 times - four orders of magnitude - when compared with performing the convolutions explicitly on the same hardware. While mean average precision over the full set of 100,000 object classes is around 0.16 due in large part to the challenges in gathering training data and collecting ground truth for so many classes, we achieve a mAP of at least 0.20 on a third of the classes and 0.30 or better on about 20% of the classes.Keywords
This publication has 15 references indexed in Scilit:
- Steerable part modelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- Learning a category independent object detection cascadePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- The power of comparative reasoningPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Mining of Massive DatasetsPublished by Cambridge University Press (CUP) ,2011
- A coarse-to-fine approach for fast deformable object detectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- What is an object?Published by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Multiple kernels for object detectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- Training-Free, Generic Object Detection Using Locally Adaptive Regression KernelsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2009
- FreebasePublished by Association for Computing Machinery (ACM) ,2008
- Robust Real-Time Face DetectionInternational Journal of Computer Vision, 2004