Automatic and accurate detection of anatomical landmarks is an essential operation in medical image analysis with a multitude of applications. Recent deep learning methods have improved results by directly encoding the appearance of the captured anatomy with the likelihood maps (i.e., heatmaps). However, most current solutions overlook another essence of heatmap regression, the objective metric for regressing target heatmaps and rely on hand-crafted heuristics to set the target precision, thus being usually cumbersome and task-specific. In this paper, we propose a novel learning-to-learn framework for landmark detection to optimize the neural network and the target precision simultaneously. The pivot of this work is to leverage the reinforcement learning (RL) framework to search objective metrics for regressing multiple heatmaps dynamically during the training process, thus avoiding setting problem-specific target precision. We also introduce an early-stop strategy for active termination of the RL agent's interaction that adapts the optimal precision for separate targets considering exploration-exploitation tradeoffs. This approach shows better stability in training and improved localization accuracy in inference. Extensive experimental results on two different applications of landmark localization: 1) our in-house prenatal ultrasound (US) dataset and 2) the publicly available dataset of cephalometric X-Ray landmark detection, demonstrate the effectiveness of our proposed method. Our proposed framework is general and shows the potential to improve the efficiency of anatomical landmark detection.

With the rapid development in artificial intelligence, social computing has evolved beyond social informatics toward the birth of social intelligence systems. This paper, therefore, takes initiatives to propose a social behaviour understanding framework with the use of deep neural networks for social and behavioural analysis. The integration of information fusion, person and object detection, social signal understanding, behaviour understanding, and context understanding plays a harmonious role to elicit social behaviours. Three systems, including depression detection, activity recognition and cognitive impairment screening, are developed to evidently demonstrate the importance of social intelligence. The study considerably contributes to the cumulative development of social computing and health informatics. It also provides a number of implications for academic bodies, healthcare practitioners, and developers of socially intelligent agents.

As an important part of Artificial Intelligence (AI), Question Answering (QA) aims at generating answers to questions phrased in natural language. While there has been substantial progress in open-domain question answering, QA systems are still struggling to answer questions which involve geographic entities or concepts and that require spatial operations. In this paper, we discuss the problem of geographic question answering (GeoQA). We first investigate the reasons why geographic questions are difficult to answer by analyzing challenges of geographic questions. We discuss the uniqueness of geographic questions compared to general QA. Then we review existing work on GeoQA and classify them by the types of questions they can address. Based on this survey, we provide a generic classification framework for geographic questions. Finally, we conclude our work by pointing out unique future research directions for GeoQA.

While imitation learning for vision based autonomous mobile robot navigation has recently received a great deal of attention in the research community, existing approaches typically require state action demonstrations that were gathered using the deployment platform. However, what if one cannot easily outfit their platform to record these demonstration signals or worse yet the demonstrator does not have access to the platform at all? Is imitation learning for vision based autonomous navigation even possible in such scenarios? In this work, we hypothesize that the answer is yes and that recent ideas from the Imitation from Observation (IfO) literature can be brought to bear such that a robot can learn to navigate using only ego centric video collected by a demonstrator, even in the presence of viewpoint mismatch. To this end, we introduce a new algorithm, Visual Observation only Imitation Learning for Autonomous navigation (VOILA), that can successfully learn navigation policies from a single video demonstration collected from a physically different agent. We evaluate VOILA in the photorealistic AirSim simulator and show that VOILA not only successfully imitates the expert, but that it also learns navigation policies that can generalize to novel environments. Further, we demonstrate the effectiveness of VOILA in a real world setting by showing that it allows a wheeled Jackal robot to successfully imitate a human walking in an environment using a video recorded using a mobile phone camera.

The proliferation of fake news, i.e., news intentionally spread for misinformation, poses a threat to individuals and society. Despite various fact-checking websites such as PolitiFact, robust detection techniques are required to deal with the increase in fake news. Several deep learning models show promising results for fake news classification, however, their black-box nature makes it difficult to explain their classification decisions and quality-assure the models. We here address this problem by proposing a novel interpretable fake news detection framework based on the recently introduced Tsetlin Machine (TM). In brief, we utilize the conjunctive clauses of the TM to capture lexical and semantic properties of both true and fake news text. Further, we use the clause ensembles to calculate the credibility of fake news. For evaluation, we conduct experiments on two publicly available datasets, PolitiFact and GossipCop, and demonstrate that the TM framework significantly outperforms previously published baselines by at least $5\%$ in terms of accuracy, with the added benefit of an interpretable logic-based representation. Further, our approach provides higher F1-score than BERT and XLNet, however, we obtain slightly lower accuracy. We finally present a case study on our model's explainability, demonstrating how it decomposes into meaningful words and their negations.

Deep neural networks are found to be prone to adversarial examples which could deliberately fool the model to make mistakes. Recently, a few of works expand this task from 2D image to 3D point cloud by using global point cloud optimization. However, the perturbations of global point are not effective for misleading the victim model. First, not all points are important in optimization toward misleading. Abundant points account considerable distortion budget but contribute trivially to attack. Second, the multi-label optimization is suboptimal for adversarial attack, since it consumes extra energy in finding multi-label victim model collapse and causes instance transformation to be dissimilar to any particular instance. Third, the independent adversarial and perceptibility losses, caring misclassification and dissimilarity separately, treat the updating of each point equally without a focus. Therefore, once perceptibility loss approaches its budget threshold, all points would be stock in the surface of hypersphere and attack would be locked in local optimality. Therefore, we propose a local aggressive adversarial attacks (L3A) to solve above issues. Technically, we select a bunch of salient points, the high-score subset of point cloud according to gradient, to perturb. Then a flow of aggressive optimization strategies are developed to reinforce the unperceptive generation of adversarial examples toward misleading victim models. Extensive experiments on PointNet, PointNet++ and DGCNN demonstrate the state-of-the-art performance of our method against existing adversarial attack methods.

To model and forecast flight delays accurately, it is crucial to harness various vehicle trajectory and contextual sensor data on airport tarmac areas. These heterogeneous sensor data, if modelled correctly, can be used to generate a situational awareness map. Existing techniques apply traditional supervised learning methods onto historical data, contextual features and route information among different airports to predict flight delay are inaccurate and only predict arrival delay but not departure delay, which is essential to airlines. In this paper, we propose a vision-based solution to achieve a high forecasting accuracy, applicable to the airport. Our solution leverages a snapshot of the airport situational awareness map, which contains various trajectories of aircraft and contextual features such as weather and airline schedules. We propose an end-to-end deep learning architecture, TrajCNN, which captures both the spatial and temporal information from the situational awareness map. Additionally, we reveal that the situational awareness map of the airport has a vital impact on estimating flight departure delay. Our proposed framework obtained a good result (around 18 minutes error) for predicting flight departure delay at Los Angeles International Airport.

Previous transfer methods for anomaly detection generally assume the availability of labeled data in source or target domains. However, such an assumption is not valid in most real applications where large-scale labeled data are too expensive. Therefore, this paper proposes an importance weighted adversarial autoencoder-based method to transfer anomaly detection knowledge in an unsupervised manner, particularly for a rarely studied scenario where a target domain has no labeled normal/abnormal data while only normal data from a related source domain exist. Specifically, the method learns to align the distributions of normal data in both source and target domains, but leave the distribution of abnormal data in the target domain unchanged. In this way, an obvious gap can be produced between the distributions of normal and abnormal data in the target domain, therefore enabling the anomaly detection in the domain. Extensive experiments on multiple synthetic datasets and the UCSD benchmark demonstrate the effectiveness of our approach.

In this talk, Yejin mainly talks about abduction and counterfactual reasoning and mentions that although they're different, both involve nonmonotonic reasoning with past context X and future constraint Z. Using language models such as GPT2 bc they are only good at conditioning on the past and we can incorporate the future by incorporating both past and future as the past with a special token in between. But this doesn't generalize well to out-of-domain distribution. So they propose to use back-prop as an inference time algorithm rather than training time only for abduction. For counterfactual reasoning, the same works just need to change the loss function to K-L divergence.

Machine learning (ML) models have been deployed successfully across a variety of use cases and industries, but due to the high computational complexity of recent ML models such as deep neural networks, inference deployments have been limited by performance and cost constraints. To add to the challenge, preparing a model for inference involves packaging the model in the right format and optimizing the model for each target hardware such as CPU, GPU, or AWS Inferentia. ML acceleration technologies have evolved to close the gap between productivity-focused ML frameworks and performance-oriented and efficiency-oriented hardware backends. However, optimizing a model for target hardware still involves assembling a complex tool chain of framework-specific converters and hardware-specific compilers, each with their own dependencies and configuration choices that can be difficult to understand, and then using it to compile the model. Amazon SageMaker is a fully managed service that enables data scientists and developers to build, train, and deploy ML models at 50% lower total cost of ownership than self-managed deployments on Amazon Elastic Compute Cloud (Amazon EC2).