In autonomous driving, data augmentation is commonly used for improving 3D object detection. The most basic methods include insertion of copied objects and rotation and scaling of the entire training frame. Numerous variants have been developed as well. The existing methods, however, are considerably limited when compared to the variety of the real world possibilities. In this work, we develop a diversified and realistic augmentation method that can flexibly construct a whole-body object, freely locate and rotate the object, and apply self-occlusion and external-occlusion accordingly. To improve the diversity of the whole-body object construction, we develop an iterative method that stochastically combines multiple objects observed from the real world into a single object. Unlike the existing augmentation methods, the constructed objects can be randomly located and rotated in the training frame because proper occlusions can be reflected to the whole-body objects in the final step. Finally, proper self-occlusion at each local object level and external-occlusion at the global frame level are applied using the Hidden Point Removal (HPR) algorithm that is computationally efficient. HPR is also used for adaptively controlling the point density of each object according to the object's distance from the LiDAR. Experiment results show that the proposed DR.CPO algorithm is data-efficient and model-agnostic without incurring any computational overhead. Also, DR.CPO can improve mAP performance by 2.08% when compared to the best 3D detection result known for KITTI dataset.

With the recent success of deep learning on a variety of applications, efficiently tuning hyperparameters of Deep Neural Networks (DNNs) with less effort has become a timely and practical topic. As an algorithmic solution, automatic hyperparameter optimization methods like Bayesian optimization have gained popularity for achieving human-comparable or even human-surpassing performance. To further speed up hyperparameter optimization, learning curves of DNNs can be predicted and used to early terminate the training phase of the chosen hyperparameter setting when the expected training performance is not satisfactory. While the previous studies show promising results, it is still unclear if an effective general rule can be derived for a broad spectrum of DNN hyperparameter optimization problems. In this work, we consider hyperparameter optimization of MNIST and CIFAR-10, and for each task, we analyze the characteristics of the 20,000 learning curves that correspond to the 20,000 different hyperparameter configurations. By investigating a large number of learning curves for a given task, we find that the characteristics of learning curve shapes can drastically change depending on the choice and range of hyperparameters. Therefore, utilizing learning curves for speed improvement is not a simple task and can be dependent on many factors. Based on the observations and analyses on the 20,000 learning curves, we design two early termination rules, ETR-1 and ETR-2, and show that the rules can be beneficial in the best case but can be harmful as well. Our observations and experimental results highlight that hyperparameter optimization of DNNs using learning curve prediction is challenging. In particular, the results of recent studies that are based on at most thousands of learning curves of a limited number of tasks should be carefully interpreted depending on the task, DNN model, hyperparameter choice, and hyperparameter range.

The evolution of Web 2.0 technologies makes web applications prevalent in various platforms including mobile devices and smart TVs. While one of the driving technologies of web applications is JavaScript, the extremely dynamic features of JavaScript make it very difficult to define and detect errors in JavaScript applications. The problem becomes more important and complicated for JavaScript web applications which may lead to severe security vulnerabilities. To help developers write safe JavaScript web applications using vendor-specific Web APIs, vendors specify their APIs often in Web IDL, which enables both API writers and users to communicate better by understanding the expected behaviors of the Web APIs. In this paper, we present SAFEWAPI, a tool to analyze Web APIs and JavaScript web applications that use the Web APIs and to detect possible misuses of Web APIs by the web applications. Even though the JavaScript language semantics allows to call a function defined with some parameters without any arguments, platform developers may require application writers to provide the exact number of arguments. Because the library functions in Web APIs expose their intended semantics clearly to web application developers unlike pure JavaScript functions, we can detect wrong uses of Web APIs precisely. For representative misuses of Web APIs defined by software quality assurance engineers, our SAFEWAPI detects such misuses in real-world JavaScript web applications.