Timezone: »
The design of low-level image features is critical for computer vision algorithms. Orientation histograms, such as those in SIFT~\cite{Lowe2004Distinctive} and HOG~\cite{Dalal2005Histograms}, are the most successful and popular features for visual object and scene recognition. We highlight the kernel view of orientation histograms, and show that they are equivalent to a certain type of match kernels over image patches. This novel view allows us to design a family of kernel descriptors which provide a unified and principled framework to turn pixel attributes (gradient, color, local binary pattern, \etc) into compact patch-level features. In particular, we introduce three types of match kernels to measure similarities between image patches, and construct compact low-dimensional kernel descriptors from these match kernels using kernel principal component analysis (KPCA)~\cite{Scholkopf1998Nonlinear}. Kernel descriptors are easy to design and can turn any type of pixel attribute into patch-level features. They outperform carefully tuned and sophisticated features including SIFT and deep belief networks. We report superior performance on standard image classification benchmarks: Scene-15, Caltech-101, CIFAR10 and CIFAR10-ImageNet.
Author Information
Liefeng Bo (Intel Labs)
Xiaofeng Ren (Intel Labs)
Dieter Fox (University of Washington)
Related Events (a corresponding poster, oral, or spotlight)
-
2010 Spotlight: Kernel Descriptors for Visual Recognition »
Tue. Dec 7th 07:50 -- 07:55 PM Room Regency Ballroom
More from the Same Authors
-
2022 : CabiNet: Scaling Neural Collision Detection for Object Rearrangement with Procedural Scene Generation »
Adithyavairavan Murali · Arsalan Mousavian · Clemens Eppner · Adam Fishman · Dieter Fox -
2022 : ProgPrompt: Generating Situated Robot Task Plans using Large Language Models »
Ishika Singh · Valts Blukis · Arsalan Mousavian · Ankit Goyal · Danfei Xu · Jonathan Tremblay · Dieter Fox · Jesse Thomason · Animesh Garg -
2022 : Learning Successor Feature Representations to Train Robust Policies for Multi-task Learning »
Melissa Mozifian · Dieter Fox · David Meger · Fabio Ramos · Animesh Garg -
2012 Poster: Discriminatively Trained Sparse Code Gradients for Contour Detection »
Xiaofeng Ren · Liefeng Bo -
2012 Poster: Unsupervised template learning for fine-grained object recognition »
Shulin Yang · Liefeng Bo · Jue Wang · Linda Shapiro -
2012 Spotlight: Discriminatively Trained Sparse Code Gradients for Contour Detection »
Xiaofeng Ren · Liefeng Bo -
2011 Poster: Hierarchical Matching Pursuit for Recognition: Architecture and Fast Algorithms »
Liefeng Bo · Xiaofeng Ren · Dieter Fox -
2009 Poster: Efficient Match Kernel between Sets of Features for Visual Recognition »
Liefeng Bo · Cristian Sminchisescu -
2009 Spotlight: Efficient Match Kernel between Sets of Features for Visual Recognition »
Liefeng Bo · Cristian Sminchisescu -
2009 Poster: Conditional Neural Fields »
Jian Peng · Liefeng Bo · Jinbo Xu