Leveraging Multiple Features for Image Retrieval and Matching

The goal of image retrieval and matching is to find and locate object instances in images from a large-scale image database. While visual features are abundant, how to combine them to improve performance by individual features remains a challenging task. In this work, we focus on leveraging multiple features for accurate and efficient image retrieval and matching. We first propose two graph-based approaches to rerank initially retrieved images for generic image retrieval. In the graph, vertices are images while edges are similarities between image pairs. Our first approach employs a mixture Markov model based on a random walk model on multiple graphs to fuse graphs. We introduce a probabilistic model to compute the importance of each feature for graph fusion under a naive Bayesian formulation, which requires statistics of similarities from a manually labeled dataset containing irrelevant images. To reduce human labeling, we further propose a fully unsupervised reranking algorithm based on a submodular objective function that can be efficiently optimized by greedy algorithm. By maximizing an information gain term over the graph, our submodular function favors a subset of database images that are similar to query images and resemble each other. The function also exploits the rank relationships of images from multiple ranked lists obtained by different features. We then study a more well-defined application, person re-identification, where the database contains labeled images of human bodies captured by multiple cameras. Re-identifications from multiple cameras are regarded as related tasks to exploit shared information. We apply a novel multi-task learning algorithm using both low level features and attributes. A low rank attribute embedding is joint learned within the multi-task learning formulation to embed original binary attributes to a continuous attribute space, where incorrect and incomplete attributes are rectified and recovered. To locate objects in images, we design an object detector based on object proposals and deep convolutional neural networks (CNN) in view of the emergence of deep networks. We improve a Fast RCNN framework and investigate two new strategies to detect objects accurately and efficiently: scale-dependent pooling (SDP) and cascaded rejection classifiers (CRC). The SDP improves detection accuracy by exploiting appropriate convolutional features depending on the scale of input object proposals. The CRC effectively utilizes convolutional features and greatly eliminates negative proposals in a cascaded manner, while maintaining a high recall for true objects. The two strategies together improve the detection accuracy and reduce the computational cost.

Tensor Completion for Multidimensional Inverse Problems with Applications to Magnetic Resonance Relaxometry

This thesis deals with tensor completion for the solution of multidimensional inverse problems. We study the problem of reconstructing an approximately low rank tensor from a small number of noisy linear measurements. New recovery guarantees, numerical algorithms, non-uniform sampling strategies, and parameter selection algorithms are developed. We derive a fixed point continuation algorithm for tensor completion and prove its convergence. A restricted isometry property (RIP) based tensor recovery guarantee is proved. Probabilistic recovery guarantees are obtained for sub-Gaussian measurement operators and for measurements obtained by non-uniform sampling from a Parseval tight frame. We show how tensor completion can be used to solve multidimensional inverse problems arising in NMR relaxometry. Algorithms are developed for regularization parameter selection, including accelerated k-fold cross-validation and generalized cross-validation. These methods are validated on experimental and simulated data. We also derive condition number estimates for nonnegative least squares problems. Tensor recovery promises to significantly accelerate N-dimensional NMR relaxometry and related experiments, enabling previously impractical experiments. Our methods could also be applied to other inverse problems arising in machine learning, image processing, signal processing, computer vision, and other fields.

ESSAYS ON THE WTO ACCESSION, HOUSEHOLD INCOME AND MULTIDIMENSIONAL POVERTY: EVIDENCE FROM CHINA

In the course of integrating into the global market, especially since China’s WTO accession, China has achieved remarkable GDP growth and has become the second largest economy in the world. These economic achievements have substantially increased Chinese incomes and have generated more government revenue for social progress. However, China’s economic progress, in itself, is neither sufficient for achieving desirable development outcomes nor a guarantee for expanding peoples’ capabilities. In fact, a narrow emphasis on GDP growth proves to be unsustainable, and may eventually harm the life quality of Chinese citizens. Without the right set of policies, a deepening trade-openness policy in China may enlarge social disparities and some people may further be deprived of basic public services and opportunities. To address these concerns, this dissertation, a set of three essays in Chapters 2-4, examines the impact of China's WTO accession on income distribution, compares China’s income and multidimensional poverty reduction and investigates the factors, including the WTO accession, that predict multidimensional poverty. By exploiting the exogenous variation in exposure to tariff changes across provinces and over time, Chapter 2 (Essay 1) estimates the causal effects of trade shocks and finds that China’s WTO accession has led to an increase in average household income, but its impacts are not evenly distributed. Households in urban areas have benefited more significantly than those in rural areas. Households with members working in the private sector have benefited more significantly than those in the public sector. However, the WTO accession has contributed to reducing income inequality between higher and lower income groups. Chapter 3 (Essay 2) explains and applies the Alkire and Foster Method (AF Method), examines multidimensional poverty in China and compares it with income poverty. It finds that China’s multidimensional poverty has declined dramatically during the period from 1989-2011. Reduction rates and patterns, however, vary by dimensions: multidimensional poverty reduction exhibits unbalanced regional progress as well as varies by province and between rural and urban areas. In comparison with income poverty, multidimensional poverty reduction does not always coincide with economic growth. Moreover, if one applies a single measure ─ either that of income or multidimensional poverty ─ a certain proportion of those who are poor remain unrecognized. By applying a logistic regression model, Chapter 4 (Essay 3) examines factors that predict multidimensional poverty and finds that the major factors predicting multidimensional poverty in China include household size, education level of the household head, health insurance coverage, geographic location, and the openness of the local economy. In order to alleviate multidimensional poverty, efforts should be targeted to (i) expand education opportunities for the household heads with low levels of education, (ii) develop appropriate geographic policies to narrow regional gaps and (iii) make macroeconomic policies work for the poor.

Essays on Matching Markets and Their Equilibria

Matching theory and matching markets are a core component of modern economic theory and market design. This dissertation presents three original contributions to this area. The first essay constructs a matching mechanism in an incomplete information matching market in which the positive assortative match is the unique efficient and unique stable match. The mechanism asks each agent in the matching market to reveal her privately known type. Through its novel payment rule, truthful revelation forms an ex post Nash equilibrium in this setting. This mechanism works in one-, two- and many-sided matching markets, thus offering the first mechanism to unify these matching markets under a single mechanism design framework. The second essay confronts a problem of matching in an environment in which no efficient and incentive compatible matching mechanism exists due to matching externalities. I develop a two-stage matching game in which a contracting stage facilitates subsequent conditionally efficient and incentive compatible Vickrey auction stage. Infinite repetition of this two-stage matching game enforces the contract in every period. This mechanism produces inequitably distributed social improvement: parties to the contract receive all of the gains and then some. The final essay demonstrates the existence of prices which stably and efficiently partition a single set of agents into firms and workers, and match those two sets to each other. This pricing system extends Kelso and Crawford's general equilibrium results in a labor market matching model and links one- and two-sided matching markets as well.