In this paper, we propose a compact network called CUNet (compact unsupervised network) to counter the image classification challenge. Different from the traditional convolutional neural networks learning filters by the timeconsuming stochastic gradient descent, CUNet learns the filter bank from diverse image patches with the simple K-means, which significantly avoids the requirement of scarce labeled training images, reduces the training consumption, and maintains the high discriminative ability. Besides, we propose a new pooling method named weighted pooling considering the different weight values of adjacent neurons, which helps to improve the robustness to small image distortions. In the output layer, CUNet integrates the feature maps gained in the last hidden layer, and straightforwardly computes histograms in non-overlapped blocks. To reduce feature redundancy, we implement the max-pooling operation on adjacent blocks to select the most competitive features. Comprehensive experiments are conducted to demonstrate the stateof-the-art classification performances with CUNet on CIFAR-10, STL-10, MNIST and Caltech101 benchmark datasets.

Along with the enlargement of image scale, convolutional local features, such as SIFT, are ineffective for representing or indexing and more compact visual representations are required. Due to the intrinsic mechanism, state-of-the-art Vector of Locally Aggregated Descriptors (VLAD) has a few limits. Based on this, we propose a new descriptor named Holons Visual Representation (HVR). The proposed HVR is a derivative mutational self-contained combination of global and local information. It exploits both global characteristics and the statistic information of local descriptors in the image dataset. It also takes advantages of local features of each image and computes their distribution with respect to the entire local descriptor space. Accordingly, the HVR is computed by a twolayer hierarchical scheme, which splits the local feature space and obtains raw partitions, as well as, the corresponding refined partitions. Then according to the distances from the centroids of partition spaces to local features and their spatial correlation, we assign the local features into their nearest raw partitions and refined partitions to obtain the global description of an image. Compared with VLAD, HVR holds critical structure information and enhances the discriminative power of individual representation with a small amount of computation cost, while using the same memory overhead. Extensive experiments on several benchmark datasets demonstrate that the proposed HVR outperforms conventional approaches in terms of scalability as well as retrieval accuracy for images with similar intra local information.

In this paper, a kernel choice method is proposed for domain adaption, referred to as Optimal Kernel Choice Domain Adaption (OKCDA). It learns a robust classier and parameters associate with Multiple Kernel Learning side by side. Domain adaption kernel-based learning strategy has shown outstanding performance. It embeds two domains of different distributions, namely, the auxiliary and the target domains, into Hilbert Space, and exploits the labeled data from the source domain to train a robust kernel-based SVM classier for the target domain. We reduce the distributions mismatch by setting up a test statistic between the two domains based on the Maximum Mean Discrepancy (MMD) algorithm and minimize the Type II error, given an upper bound on error I. Simultaneously, we minimize the structural risk functional. In order to highlight the advantages of the proposed method, we tackle a text classication problem on 20 Newsgroups dataset and Email Spam dataset. The results demonstrate that our method exhibits outstanding performance.

No abstract

No abstract