With the rapid development of intelligent detection algorithms based on deep learning, much progress has been made in automatic road defect recognition and road marking parsing. This can effectively address the issue of an expensive and time-consumin
g process for professional inspectors to review the street manually. Towards this goal, we present RoadAtlas, a novel end-to-end integrated system that can support 1) road defect detection, 2) road marking parsing, 3) a web-based dashboard for presenting and inputting data by users, and 4) a backend containing a well-structured database and developed APIs.
Item response theory (IRT) has become one of the most popular statistical models for psychometrics, a field of study concerned with the theory and techniques of psychological measurement. The IRT models are latent factor models tailored to the analys
is, interpretation, and prediction of individuals behaviors in answering a set of measurement items that typically involve categorical response data. Many important questions of measurement are directly or indirectly answered through the use of IRT models, including scoring individuals test performances, validating a test scale, linking two tests, among others. This paper provides a review of item response theory, including its statistical framework and psychometric applications. We establish connections between item response theory and related topics in statistics, including empirical Bayes, nonparametric methods, matrix completion, regularized estimation, and sequential analysis. Possible future directions of IRT are discussed from the perspective of statistical learning.
The capabilities of autonomous flight with unmanned aerial vehicles (UAVs) have significantly increased in recent times. However, basic problems such as fast and robust geo-localization in GPS-denied environments still remain unsolved. Existing resea
rch has primarily concentrated on improving the accuracy of localization at the cost of long and varying computation time in various situations, which often necessitates the use of powerful ground station machines. In order to make image-based geo-localization online and pragmatic for lightweight embedded systems on UAVs, we propose a framework that is reliable in changing scenes, flexible about computing resource allocation and adaptable to common camera placements. The framework is comprised of two stages: offline database preparation and online inference. At the first stage, color images and depth maps are rendered as seen from potential vehicle poses quantized over the satellite and topography maps of anticipated flying areas. A database is then populated with the global and local descriptors of the rendered images. At the second stage, for each captured real-world query image, top global matches are retrieved from the database and the vehicle pose is further refined via local descriptor matching. We present field experiments of image-based localization on two different UAV platforms to validate our results.
Modern communication platforms such as Gitter and Slack play an increasingly critical role in supporting software teamwork, especially in open source development.Conversations on such platforms often contain intensive, valuable information that may b
e used for better understanding OSS developer communication and collaboration. However, little work has been done in this regard. To bridge the gap, this paper reports a first comprehensive empirical study on developers live chat, investigating when they interact, what community structures look like, which topics are discussed, and how they interact. We manually analyze 749 dialogs in the first phase, followed by an automated analysis of over 173K dialogs in the second phase. We find that developers tend to converse more often on weekdays, especially on Wednesdays and Thursdays (UTC), that there are three common community structures observed, that developers tend to discuss topics such as API usages and errors, and that six dialog interaction patterns are identified in the live chat communities. Based on the findings, we provide recommendations for individual developers and OSS communities, highlight desired features for platform vendors, and shed light on future research directions. We believe that the findings and insights will enable a better understanding of developers live chat, pave the way for other researchers, as well as a better utilization and mining of knowledge embedded in the massive chat history.
In this paper, we introduce Target-Aware Weighted Training (TAWT), a weighted training algorithm for cross-task learning based on minimizing a representation-based task distance between the source and target tasks. We show that TAWT is easy to implem
ent, is computationally efficient, requires little hyperparameter tuning, and enjoys non-asymptotic learning-theoretic guarantees. The effectiveness of TAWT is corroborated through extensive experiments with BERT on four sequence tagging tasks in natural language processing (NLP), including part-of-speech (PoS) tagging, chunking, predicate detection, and named entity recognition (NER). As a byproduct, the proposed representation-based task distance allows one to reason in a theoretically principled way about several critical aspects of cross-task learning, such as the choice of the source data and the impact of fine-tuning
Cross-modal attention mechanisms have been widely applied to the image-text matching task and have achieved remarkable improvements thanks to its capability of learning fine-grained relevance across different modalities. However, the cross-modal atte
ntion models of existing methods could be sub-optimal and inaccurate because there is no direct supervision provided during the training process. In this work, we propose two novel training strategies, namely Contrastive Content Re-sourcing (CCR) and Contrastive Content Swapping (CCS) constraints, to address such limitations. These constraints supervise the training of cross-modal attention models in a contrastive learning manner without requiring explicit attention annotations. They are plug-in training strategies and can be easily integrated into existing cross-modal attention models. Additionally, we introduce three metrics including Attention Precision, Recall, and F1-Score to quantitatively measure the quality of learned attention models. We evaluate the proposed constraints by incorporating them into four state-of-the-art cross-modal attention-based image-text matching models. Experimental results on both Flickr30k and MS-COCO datasets demonstrate that integrating these constraints improves the model performance in terms of both retrieval performance and attention metrics.
A widely recognized difficulty in federated learning arises from the statistical heterogeneity among clients: local datasets often come from different but not entirely unrelated distributions, and personalization is, therefore, necessary to achieve o
ptimal results from each individuals perspective. In this paper, we show how the excess risks of personalized federated learning with a smooth, strongly convex loss depend on data heterogeneity from a minimax point of view. Our analysis reveals a surprising theorem of the alternative for personalized federated learning: there exists a threshold such that (a) if a certain measure of data heterogeneity is below this threshold, the FedAvg algorithm [McMahan et al., 2017] is minimax optimal; (b) when the measure of heterogeneity is above this threshold, then doing pure local training (i.e., clients solve empirical risk minimization problems on their local datasets without any communication) is minimax optimal. As an implication, our results show that the presumably difficult (infinite-dimensional) problem of adapting to client-wise heterogeneity can be reduced to a simple binary decision problem of choosing between the two baseline algorithms. Our analysis relies on a new notion of algorithmic stability that takes into account the nature of federated learning.
Federated learning (FL) is a training paradigm where the clients collaboratively learn models by repeatedly sharing information without compromising much on the privacy of their local sensitive data. In this paper, we introduce federated $f$-differen
tial privacy, a new notion specifically tailored to the federated setting, based on the framework of Gaussian differential privacy. Federated $f$-differential privacy operates on record level: it provides the privacy guarantee on each individual record of one clients data against adversaries. We then propose a generic private federated learning framework {PriFedSync} that accommodates a large family of state-of-the-art FL algorithms, which provably achieves federated $f$-differential privacy. Finally, we empirically demonstrate the trade-off between privacy guarantee and prediction performance for models trained by {PriFedSync} in computer vision tasks.
In network applications, it has become increasingly common to obtain datasets in the form of multiple networks observed on the same set of subjects, where each network is obtained in a related but different experiment condition or application scenari
o. Such datasets can be modeled by multilayer networks where each layer is a separate network itself while different layers are associated and share some common information. The present paper studies community detection in a stylized yet informative inhomogeneous multilayer network model. In our model, layers are generated by different stochastic block models, the community structures of which are (random) perturbations of a common global structure while the connecting probabilities in different layers are not related. Focusing on the symmetric two block case, we establish minimax rates for both emph{global estimation} of the common structure and emph{individualized estimation} of layer-wise community structures. Both minimax rates have sharp exponents. In addition, we provide an efficient algorithm that is simultaneously asymptotic minimax optimal for both estimation tasks under mild conditions. The optimal rates depend on the emph{parity} of the number of most informative layers, a phenomenon that is caused by inhomogeneity across layers.
As a popular approach to modeling the dynamics of training overparametrized neural networks (NNs), the neural tangent kernels (NTK) are known to fall behind real-world NNs in generalization ability. This performance gap is in part due to the textit{l
abel agnostic} nature of the NTK, which renders the resulting kernel not as textit{locally elastic} as NNs~citep{he2019local}. In this paper, we introduce a novel approach from the perspective of emph{label-awareness} to reduce this gap for the NTK. Specifically, we propose two label-aware kernels that are each a superimposition of a label-agnostic part and a hierarchy of label-aware parts with increasing complexity of label dependence, using the Hoeffding decomposition. Through both theoretical and empirical evidence, we show that the models trained with the proposed kernels better simulate NNs in terms of generalization ability and local elasticity.
