Kernel Descriptors for Visual Recognition
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Attributeimage-classificationImage ClassificationScene RecognitionSimilar Papers 제목 키워드 기반
Supervised Kernel Descriptors for Visual Recognition
In visual recognition tasks, the design of low level image feature representation is fundamental. The advent of local patch features from pixel attributes such as SIFT and LBP, has precipitated dramatic progresses. Recen…
General Classificationimage-classificationImage ClassificationDeepKSPD: Learning Kernel-matrix-based SPD Representation for Fine-grained Image Recognition
Being symmetric positive-definite (SPD), covariance matrix has traditionally been used to represent a set of local descriptors in visual recognition. Recent study shows that kernel matrix can give considerably better rep…
Fine-Grained Image RecognitionMultiple Kernel Sparse Representations for Supervised and Unsupervised Learning
In complex visual recognition tasks it is typical to adopt multiple descriptors, that describe different aspects of the images, for obtaining an improved recognition performance. Descriptors that have diverse forms can b…
ClusteringDictionary LearningGraph EmbeddingImage Clustering+1Multi-View Super Vector for Action Recognition
Images and videos are often characterized by multiple types of local descriptors such as SIFT, HOG and HOF, each of which describes certain aspects of object feature. Recognition systems benefit from fusing multiple type…
Action RecognitionTemporal Action LocalizationLearning and aggregating deep local descriptors for instance-level recognition
We propose an efficient method to learn deep local descriptors for instance-level recognition. The training only requires examples of positive and negative image pairs and is performed as metric learning of sum-pooled gl…
Image RetrievalMetric Learning