Object Recognition with Hierarchical Kernel Descriptors
   Liefeng Bo, Kevin Lai, Xiaofeng Ren, and Dieter Fox, at CVPR 2011


Kernel descriptors [Bo et al NIPS 2010] provide a unified way to gener- ate rich visual feature sets by turning pixel attributes into patch-level features, and yield impressive results on many object recognition tasks. However, best results with ker- nel descriptors are achieved using efficient match kernels in conjunction with nonlinear SVMs, which makes it impracti- cal for large-scale problems. In this paper, we propose hi- erarchical kernel descriptors that apply kernel descriptors recursively to form image-level features and thus provide a conceptually simple and consistent way to generate image- level features from pixel attributes. More importantly, hier- archical kernel descriptors allow linear SVMs to yield state- of-the-art accuracy while being scalable to large datasets. They can also be naturally extended to extract features over depth images. We evaluate hierarchical kernel descriptors both on the CIFAR10 dataset and the new RGB-D Object Dataset consisting of segmented RGB and depth images of 300 everyday objects.