Pengcheng Wu

Online multimodal deep similarity learning with application to image retrieval

Recent years have witnessed extensive studies on distance metric learning (DML) for improving similarity search in multimedia information retrieval tasks. Despite their successes, most existing DML methods suffer from two critical limitations: (i) they typically attempt to learn a linear distance function on the input feature space, in which the assumption of linearity limits their capacity of measuring the similarity on complex patterns in real-world applications; (ii) they are often designed for learning distance metrics on uni-modal data, which may not effectively handle the similarity measures for multimedia objects with multimodal representations. To address these limitations, in this paper, we propose a novel framework of online multimodal deep similarity learning (OMDSL), which aims to optimally integrate multiple deep neural networks pretrained with stacked denoising autoencoder. In particular, the proposed framework explores a unified two-stage online learning scheme that consists of (i) learning a flexible nonlinear transformation function for each individual modality, and (ii) learning to find the optimal combination of multiple diverse modalities simultaneously in a coherent process. We conduct an extensive set of experiments to evaluate the performance of the proposed algorithms for multimodal image retrieval tasks, in which the encouraging results validate the effectiveness of the proposed technique.

Mining social images with distance metric learning for automated image tagging

With the popularity of various social media applications, massive social images associated with high quality tags have been made available in many social media web sites nowadays. Mining social images on the web has become an emerging important research topic in web search and data mining. In this paper, we propose a machine learning framework for mining social images and investigate its application to automated image tagging. To effectively discover knowledge from social images that are often associated with multimodal contents (including visual images and textual tags), we propose a novel Unified Distance Metric Learning (UDML) scheme, which not only exploits both visual and textual contents of social images, but also effectively unifies both inductive and transductive metric learning techniques in a systematic learning framework. We further develop an efficient stochastic gradient descent algorithm for solving the UDML optimization task and prove the convergence of the algorithm. By applying the proposed technique to the automated image tagging task in our experiments, we demonstrate that our technique is empirically effective and promising for mining social images towards some real applications.

Boosting multi-kernel locality-sensitive hashing for scalable image retrieval

Similarity search is a key challenge for multimedia retrieval applications where data are usually represented in high-dimensional space. Among various algorithms proposed for similarity search in high-dimensional space, Locality-Sensitive Hashing (LSH) is the most popular one, which recently has been extended to Kernelized Locality-Sensitive Hashing (KLSH) by exploiting kernel similarity for better retrieval efficacy. Typically, KLSH works only with a single kernel, which is often limited in real-world multimedia applications, where data may originate from multiple resources or can be represented in several different forms. For example, in content-based multimedia retrieval, a variety of features can be extracted to represent contents of an image. To overcome the limitation of regular KLSH, we propose a novel Boosting Multi-Kernel Locality-Sensitive Hashing (BMKLSH) scheme that significantly boosts the retrieval performance of KLSH by making use of multiple kernels. We conduct extensive experiments for large-scale content-based image retrieval, in which encouraging results show that the proposed method outperforms the state-of-the-art techniques.

Face detection using deep learning: An improved faster RCNN approach

Abstract In this paper, we present a new face detection scheme using deep learning and achieve the state-of-the-art detection performance on the well-known FDDB face detection benchmark evaluation. In particular, we improve the state-of-the-art Faster RCNN framework by combining a number of strategies, including feature concatenation, hard negative mining, multi-scale training, model pre-training, and proper calibration of key parameters. As a consequence, the proposed scheme obtained the state-of-the-art face detection performance and was ranked as one of the best models in terms of ROC curves of the published methods on the FDDB benchmark. 1

Online Multi-Modal Distance Metric Learning with Application to Image Retrieval

Distance metric learning (DML) is an important technique to improve similarity search in content-based image retrieval. Despite being studied extensively, most existing DML approaches typically adopt a single-modal learning framework that learns the distance metric on either a single feature type or a combined feature space where multiple types of features are simply concatenated. Such single-modal DML methods suffer from some critical limitations: (i) some type of features may significantly dominate the others in the DML task due to diverse feature representations; and (ii) learning a distance metric on the combined high-dimensional feature space can be extremely time-consuming using the naive feature concatenation approach. To address these limitations, in this paper, we investigate a novel scheme of online multi-modal distance metric learning (OMDML), which explores a unified two-level online learning scheme: (i) it learns to optimize a distance metric on each individual feature space; and (ii) then it learns to find the optimal combination of diverse types of features. To further reduce the expensive cost of DML on high-dimensional feature space, we propose a low-rank OMDML algorithm which not only significantly reduces the computational cost but also retains highly competing or even better learning accuracy. We conduct extensive experiments to evaluate the performance of the proposed algorithms for multi-modal image retrieval, in which encouraging results validate the effectiveness of the proposed technique.

High-Dimensional Data Stream Classification via Sparse Online Learning

The amount of data in our society has been exploding in the era of big data today. In this paper, we address several open challenges of big data stream classification, including high volume, high velocity, high dimensionality, and high sparsity. Many existing studies in data mining literature solve data stream classification tasks in a batch learning setting, which suffers from poor efficiency and scalability when dealing with big data. To overcome the limitations, this paper investigates an online learning framework for big data stream classification tasks. Unlike some existing online data stream classification techniques that are often based on first-order online learning, we propose a framework of Sparse Online Classification (SOC) for data stream classification, which includes some state-of-the-art first-order sparse online learning algorithms as special cases and allows us to derive a new effective second-order online learning algorithm for data stream classification. We conduct an extensive set of experiments, in which encouraging results validate the efficacy of the proposed algorithms in comparison to a family of state-of-the-art techniques on a variety of data stream classification tasks.

Randomly projected KD-trees with distance metric learning for image retrieval

Efficient nearest neighbor (NN) search techniques for high-dimensional data are crucial to content-based image retrieval (CBIR). Traditional data structures (e.g., kd-tree) usually are only efficient for low dimensional data, but often perform no better than a simple exhaustive linear search when the number of dimensions is large enough. Recently, approximate NN search techniques have been proposed for high-dimensional search, such as Locality-Sensitive Hashing (LSH), which adopts some random projection approach. Motivated by similar idea, in this paper, we propose a new high dimensional NN search method, called Randomly Projected kd-Trees (RP-kd-Trees), which is to project data points into a lower-dimensional space so as to exploit the advantage of multiple kd-trees over low-dimensional data. Based on the proposed framework, we present an enhanced RP-kd-Trees scheme by applying distance metric learning techniques. We conducted extensive empirical studies on CBIR, which showed that our technique achieved faster search performance with better retrieval quality than regular LSH algorithms.

HDIdx: High-dimensional indexing for efficient approximate nearest neighbor search☆

Abstract Fast Nearest Neighbor (NN) search is a fundamental challenge in large-scale data processing and analytics, particularly for analyzing multimedia contents which are often of high dimensionality. Instead of using exact NN search, extensive research efforts have been focusing on approximate NN search algorithms. In this work, we present “HDIdx”, an efficient high-dimensional indexing library for fast approximate NN search, which is open-source and written in Python. It offers a family of state-of-the-art algorithms that convert input high-dimensional vectors into compact binary codes, making them very efficient and scalable for NN search with very low space complexity.