Good Feature Representation Research Articles

Multi-view clustering with extreme learning machine

Nowadays, data always have multiple representations, and a good feature representation usually leads to a good clustering performance. Existing multi-view clustering works generally integrate multiple complementary information to gain better clustering performance rather than relying on a single view. However, these works usually focus on the combination of information rather than improving the feature representation capability of each view. As a new method, extreme learning machine (ELM) has excellent feature representation capability, easy parameter selection, and promising performance in various clustering tasks. This paper proposes a novel multi-view clustering framework with ELM to further improve clustering performance, and implements three algorithms based on this framework. In this framework, the normalized features of each individual view are mapped onto a higher dimensional feature space by the ELM random mapping. Afterwards, the unsupervised multi-view clustering is performed in this feature space. Thus far, this is the first work on multi-view clustering with ELM. Numerous baseline methods on five real-world datasets are empirically compared to show the effectiveness of the proposed algorithms. As indicated, the proposed algorithms yield superior clustering performance when compared with several state-of-art multi-view clustering methods in recent literatures.

Unsupervised Feature Learning Via Spectral Clustering of Multidimensional Patches for Remotely Sensed Scene Classification

Scene classification plays an important role in the interpretation of remotely sensed high-resolution imagery. However, the performance of scene classification strongly relies on the discriminative power of feature representation, which is generally hand-engineered and requires a huge amount of domain-expert knowledge as well as time-consuming hand tuning. Recently, unsupervised feature learning (UFL) provides an alternative way to automatically learn discriminative feature representation from images. However, the performances achieved by conventional UFL methods are not comparable to the state-of-the-art, mainly due to the neglect of locally substantial image structures. This paper presents an improved UFL algorithm based on spectral clustering, named UFL-SC, which cannot only adaptively learn good local feature representations but also discover intrinsic structures of local image patches. In contrast to the standard UFL pipeline, UFL-SC first maps the original image patches into a low-dimensional and intrinsic feature space by linear manifold analysis techniques, and then learns a dictionary (e.g., using K-means clustering) on the patch manifold for feature encoding. To generate a feature representation for each local patch, an explicit parameterized feature encoding method, i.e., triangle encoding, is applied with the learned dictionary on the same patch manifold. The holistic feature representation of image scenes is finally obtained by building a bag-of-visual-words (BOW) model of the encoded local features. Experiments demonstrate that the proposed UFL-SC algorithm can extract efficient local features for image scenes and show comparable performance to the state-of-the-art approach on open scene classification benchmark.

Improving Shape Retrieval by Integrating AIR and Modified MutualkNN Graph

In computer vision, image retrieval remained a significant problem and recent resurgent of image retrieval also relies on other postprocessing methods to improve the accuracy instead of solely relying on good feature representation. Our method addressed the shape retrieval of binary images. This paper proposes a new integration scheme to best utilize feature representation along with contextual information. For feature representation we used articulation invariant representation; dynamic programming is then utilized for better shape matching followed by manifold learning based postprocessing modified mutualkNN graph to further improve the similarity score. We conducted extensive experiments on widely used MPEG-7 database of shape images by so-called bulls-eye score with and without normalization of modified mutualkNN graph which clearly indicates the importance of normalization. Finally, our method demonstrated better results compared to other methods. We also computed the computational time with another graph transduction method which clearly shows that our method is computationally very fast. Furthermore, to show consistency of postprocessing method, we also performed experiments on challenging ORL and YALE face datasets and improved baseline results.

Feature learning based on SAE–PCA network for human gesture recognition in RGBD images

Coming with the emerging of depth sensors link Microsoft Kinect, human hand gesture recognition has received ever increasing research interests recently. A successful gesture recognition system has usually heavily relied on having a good feature representation of data, which is expected to be task-dependent as well as coping with the challenges and opportunities induced by depth sensor. In this paper, a feature learning approach based on sparse auto-encoder (SAE) and principle component analysis is proposed for recognizing human actions, i.e. finger-spelling or sign language, for RGB-D inputs. The proposed model of feature learning is consisted of two components: First, features are learned respectively from the RGB and depth channels, using sparse auto-encoder with convolutional neural networks. Second, the learned features from both channels is concatenated and fed into a multiple layer PCA to get the final feature. Experimental results on American sign language (ASL) dataset demonstrate that the proposed feature learning model is significantly effective, which improves the recognition rate from 75% to 99.05% and outperforms the state-of-the-art.

Supervised Hashing for Image Retrieval via Image Representation Learning

Hashing is a popular approximate nearest neighbor search approach for large-scale image retrieval. Supervised hashing, which incorporates similarity/dissimilarity information on entity pairs to improve the quality of hashing function learning, has recently received increasing attention. However, in the existing supervised hashing methods for images, an input image is usually encoded by a vector of hand-crafted visual features. Such hand-crafted feature vectors do not necessarily preserve the accurate semantic similarities of images pairs, which may often degrade the performance of hashing function learning. In this paper, we propose a supervised hashing method for image retrieval, in which we automatically learn a good image representation tailored to hashing as well as a set of hash functions. The proposed method has two stages. In the first stage, given the pairwise similarity matrix $S$ over training images, we propose a scalable coordinate descent method to decompose $S$ into a product of $HH^T$ where $H$ is a matrix with each of its rows being the approximate hash code associated to a training image. In the second stage, we propose to simultaneously learn a good feature representation for the input images as well as a set of hash functions, via a deep convolutional network tailored to the learned hash codes in $H$ and optionally the discrete class labels of the images. Extensive empirical evaluations on three benchmark datasets with different kinds of images show that the proposed method has superior performance gains over several state-of-the-art supervised and unsupervised hashing methods.

Incremental two-dimensional kernel principal component analysis

In this paper, we propose a new online non-linear feature extraction method, called the incremental two-dimensional kernel principal component analysis (I2DKPCA), not only to reduce the computational cost but also to provide good feature representation. Batch type feature extraction methods such as principal component analysis (PCA) and two-dimensional PCA (2DPCA) require more computational time and memory usage, as they collect the entire training data to extract the basis vectors. Also, these linear feature extraction methods could not effectively represent the non-linear distribution of input data. Therefore, by adopting a non-linear kernel approach with chunk concept, the KPCA and 2DKPCA can effectively address the non-linear feature representation problem by adaptively changing the feature spaces. However, this kernel approach requires more computational time for processing images with high dimensional input data. In order to solve these problems, we combined the 2DKPCA with incremental learning for (1) solving the non-linear problem and (2) reducing the memory usage with computational time. In order to evaluate the performance of I2DKPCA, several experiments have been performed using well-known face and object image databases.

Domain Adaptation via Transfer Component Analysis

Domain adaptation allows knowledge from a source domain to be transferred to a different but related target domain. Intuitively, discovering a good feature representation across domains is crucial. In this paper, we first propose to find such a representation through a new learning method, transfer component analysis (TCA), for domain adaptation. TCA tries to learn some transfer components across domains in a reproducing kernel Hilbert space using maximum mean miscrepancy. In the subspace spanned by these transfer components, data properties are preserved and data distributions in different domains are close to each other. As a result, with the new representations in this subspace, we can apply standard machine learning methods to train classifiers or regression models in the source domain for use in the target domain. Furthermore, in order to uncover the knowledge hidden in the relations between the data labels from the source and target domains, we extend TCA in a semisupervised learning setting, which encodes label information into transfer components learning. We call this extension semisupervised TCA. The main contribution of our work is that we propose a novel dimensionality reduction framework for reducing the distance between domains in a latent space for domain adaptation. We propose both unsupervised and semisupervised feature extraction approaches, which can dramatically reduce the distance between domain distributions by projecting data onto the learned transfer components. Finally, our approach can handle large datasets and naturally lead to out-of-sample generalization. The effectiveness and efficiency of our approach are verified by experiments on five toy datasets and two real-world applications: cross-domain indoor WiFi localization and cross-domain text classification.

Static topographic modeling for facial expression recognition and analysis

Facial expression plays a key role in non-verbal face-to-face communication. It is a challenging task to develop an automatic facial expression reading and understanding system, especially, for recognizing the facial expression from a static image without any prior knowledge of the test subject. In this paper, we present a topographic modeling approach to recognize and analyze facial expression from single static images. The so-called topographic modeling is developed based on a novel facial expression descriptor, Topographic Context (TC), for representing and recognizing facial expressions. This proposed approach applies topographic analysis that treats the image as a 3D surface and labels each pixel by its terrain features. Topographic context captures the distribution of terrain labels in the expressive regions of a face. It characterizes the distinct facial expression while conserving abundant expression information and disregarding most individual characteristics. Experiments on person-dependent and person-independent facial expression recognition using two public databases (MMI and Cohn–Kanade database) show that TC is a good feature representation for recognizing basic prototypic expressions. Furthermore, we conduct the separability analysis of TC-based features by both a visualized dimensionality reduction example and a theoretical estimation using certain separability criterion. For an in-depth understanding of the recognition property of different expressions, the between-expression discriminability is also quantitatively evaluated using the separability criterion. Finally, we investigated the robustness of the extracted TC-based expression features in two aspects: the robustness to the distortion of detected face region and the robustness to different intensities of facial expressions. The experimental results show that our system achieved the best correct rate at 82.61% for the person-independent facial expression recognition.