Search

The proliferation of artificial intelligence based systems in all walks of life raises concerns about their safety and robustness, especially for cyber-physical systems including multiple machine learning components. In this paper, we introduce robustness contracts as a framework for compositional specification and reasoning about the robustness of cyber-physical systems based on neural network (NN) components. Robustness contracts can encompass and generalize a variety of notions of robustness which were previously proposed in the literature. They can seamlessly apply to NN-based perception as well as deep reinforcement learning (RL)-enabled control applications. We present a sound and complete algorithm that can efficiently verify the satisfaction of a class of robustness contracts on NNs by leveraging notions from Lagrangian duality to identify system configurations that violate the contracts. We illustrate the effectiveness of our approach on the verification of NN-based perception systems and deep RL-based control systems.

Which neighborhoods experience physical improvements? In this paper, we introduce a computer vision method to measure changes in the physical appearances of neighborhoods from time-series street-level imagery. We connect changes in the physical appearance of five US cities with economic and demographic data and find three factors that predict neighborhood improvement. First, neighborhoods that are densely populated by college-educated adults are more likely to experience physical improvements-an observation that is compatible with the economic literature linking human capital and local success. Second, neighborhoods with better initial appearances experience, on average, larger positive improvements-an observation that is consistent with "tipping" theories of urban change. Third, neighborhood improvement correlates positively with physical proximity to the central business district and to other physically attractive neighborhoods-an observation that is consistent with the "invasion" theories of urban sociology. Together, our results provide support for three classical theories of urban change and illustrate the value of using computer vision methods and street-level imagery to understand the physical dynamics of cities.

New, “big data” sources allow measurement of city characteristics and outcome variables at higher collection frequencies and more granular geographic scales than ever before. However, big data will not solve large urban social science questions on its own. Big urban data has the most value for the study of cities when it allows measurement of the previously opaque, or when it can be coupled with exogenous shocks to people or place. We describe a number of new urban data sources and illustrate how they can be used to improve the study and function of cities. We first show how Google Street View images can be used to predict income in New York City, suggesting that similar imagery data can be used to map wealth and poverty in previously unmeasured areas of the developing world. We then discuss how survey techniques can be improved to better measure willingness to pay for urban amenities. Finally, we explain how Internet data is being used to improve the quality of city services. (JEL R1, C8, C18)

Fine-Grained Visual Classification (FGVC) datasets contain small sample sizes, along with significant intra-class variation and inter-class similarity. While prior work has addressed intra-class variation using localization and segmentation techniques, inter-class similarity may also affect feature learning and reduce classification performance. In this work, we address this problem using a novel optimization procedure for the end-to-end neural network training on FGVC tasks. Our procedure, called Pairwise Confusion (PC) reduces overfitting by intentionally introducing confusion in the activations. With PC regularization, we obtain state-of-the-art performance on six of the most widely-used FGVC datasets and demonstrate improved localization ability. PC is easy to implement, does not need excessive hyperparameter tuning during training, and does not add significant overhead during test time.

Computer vision methods that quantify the perception of urban environment are increasingly being used to study the relationship between a city’s physical appearance and the behavior and health of its residents. Yet, the throughput of current methods is too limited to quantify the perception of cities across the world. To tackle this challenge, we introduce a new crowdsourced dataset containing 110,988 images from 56 cities, and 1,170,000 pairwise comparisons provided by 81,630 online volunteers along six perceptual attributes: safe, lively, boring, wealthy, depressing, and beautiful. Using this data, we train a Siamese-like convolutional neural architecture, which learns from a joint classification and ranking loss, to predict human judgments of pairwise image comparisons. Our results show that crowdsourcing combined with neural networks can produce urban perception data at the global scale.

Policy makers, urban planners, architects, sociologists, and economists are interested in creating urban areas that are both lively and safe. But are the safety and liveliness of neighborhoods independent characteristics? Or are they just two sides of the same coin? In a world where people avoid unsafe looking places, neighborhoods that look unsafe will be less lively, and will fail to harness the natural surveillance of human activity. But in a world where the preference for safe looking neighborhoods is small, the connection between the perception of safety and liveliness will be either weak or nonexistent. In this paper we explore the connection between the levels of activity and the perception of safety of neighborhoods in two major Italian cities by combining mobile phone data (as a proxy for activity or liveliness) with scores of perceived safety estimated using a Convolutional Neural Network trained on a dataset of Google Street View images scored using a crowdsourced visual perception survey. We find that: (i) safer looking neighborhoods are more active than what is expected from their population density, employee density, and distance to the city centre; and (ii) that the correlation between appearance of safety and activity is positive, strong, and significant, for females and people over 50, but negative for people under 30, suggesting that the behavioral impact of perception depends on the demographic of the population. Finally, we use occlusion techniques to identify the urban features that contribute to the appearance of safety, finding that greenery and street facing windows contribute to a positive appearance of safety (in agreement with Oscar Newman's defensible space theory). These results suggest that urban appearance modulates levels of human activity and, consequently, a neighborhood's rate of natural surveillance., Comment: To appear in the Proceedings of ACM Multimedia Conference (MM), 2016. October 15 - 19, 2016, Amsterdam, Netherlands