Scene change detection is an image processing problem related to partitioning pixels of a digital image into foreground and background regions. Mostly, visual knowledge-based computer intelligent systems, like traffic monitoring, video surveillance, and anomaly detection, need to use change detection techniques. Amongst the most prominent detection methods, there are the learning-based ones, which besides sharing similar training and testing protocols, differ from each other in terms of their architecture design strategies. Such architecture design directly impacts on the quality of the detection results, and also in the device resources capacity, like memory. In this work, we propose a novel Multiscale Cascade Residual Convolutional Neural Network that integrates multiscale processing strategy through a Residual Processing Module, with a Segmentation Convolutional Neural Network. Experiments conducted on two different datasets support the effectiveness of the proposed approach, achieving average overall $\boldsymbol{F\text{-}measure}$ results of $\boldsymbol{0.9622}$ and $\boldsymbol{0.9664}$ over Change Detection 2014 and PetrobrasROUTES datasets respectively, besides comprising approximately eight times fewer parameters. Such obtained results place the proposed technique amongst the top four state-of-the-art scene change detection methods.

In sociological research, the study of macro processes, such as opinion polarization, faces a fundamental problem, the so-called micro-macro problem. To overcome this problem, we combine empirical experimental research on biased argument processing with a computational theory of group deliberation in order to clarify the role of biased processing in debates around energy. The experiment reveals a strong tendency to consider arguments aligned with the current attitude more persuasive and to downgrade those speaking against it. This is integrated into the framework of argument communication theory in which agents exchange arguments about a certain topic and adapt opinions accordingly. We derive a mathematical model that allows to relate the strength of biased processing to expected attitude changes given the specific experimental conditions and find a clear signature of moderate biased processing. We further show that this model fits significantly better to the experimentally observed attitude changes than the neutral argument processing assumption made in previous models. Our approach provides new insight into the relationship between biased processing and opinion polarization. At the individual level our analysis reveals a sharp qualitative transition from attitude moderation to polarization. At the collective level we find (i.) that weak biased processing significantly accelerates group decision processes whereas (ii.) strong biased processing leads to a persistent conflictual state of subgroup polarization. While this shows that biased processing alone is sufficient for the emergence of polarization, we also demonstrate that homophily may lead to intra-group conflict at significantly lower rates of biased processing.

Data compression is becoming critical for storing scientific data because many scientific applications need to store large amounts of data and post process this data for scientific discovery. Unlike image and video compression algorithms that limit errors to primary data, scientists require compression techniques that accurately preserve derived quantities of interest (QoIs). This paper presents a physics-informed compression technique implemented as an end-to-end, scalable, GPU-based pipeline for data compression that addresses this requirement. Our hybrid compression technique combines machine learning techniques and standard compression methods. Specifically, we combine an autoencoder, an error-bounded lossy compressor to provide guarantees on raw data error, and a constraint satisfaction post-processing step to preserve the QoIs within a minimal error (generally less than floating point error). The effectiveness of the data compression pipeline is demonstrated by compressing nuclear fusion simulation data generated by a large-scale fusion code, XGC, which produces hundreds of terabytes of data in a single day. Our approach works within the ADIOS framework and results in compression by a factor of more than 150 while requiring only a few percent of the computational resources necessary for generating the data, making the overall approach highly effective for practical scenarios.

Raphael Zufferey, a postdoctoral fellow in the Laboratory of Intelligent Systems (LIS) and Biorobotics ab (BioRob) in the School of Engineering, is the first author on a recent Nature Communications paper describing the unique landing gear that makes such perching possible. He built and tested it in collaboration with colleagues at the University of Seville, Spain, where the 700-gram ornithopter itself was developed as part of the European project GRIFFIN. "This is the first phase of a larger project. Once an ornithopter can master landing autonomously on a tree branch, then it has the potential to carry out specific tasks, such as unobtrusively collecting biological samples or measurements from a tree. Eventually, it could even land on artificial structures, which could open up further areas of application," Zufferey says.

This is the post about the work I've done as a research assistant at Stanford. I was lucky to have Tapan Mukerji as my advisor, his guidance helped me to avoid a lot of pitfalls and keep going when I felt stuck. This post is based on my paper. The task I was working on was seismic facies classification with deep learning, and I'd like to start with a high-level overview of why this is a problem worth solving. Seismic data is used to understand the subsurface structure and, ideally, to quantify some properties indicative of where hydrocarbons may be deposited. Figure 1 shows what seismic data may look like.

Digitalization has taken over every walk of life, be it something as simple as buying a flight ticket, booking a movie, or ordering food. We are surrounded by innovations in technology like Additive Manufacturing, 3D Printing, Artificial Intelligence, IoT, Robotics, and more. Today artificial intelligence has worked wonders in arenas of problem-solving, learning, object detection, and others for household, industrial and commercial applications. One of the prime areas where AI is proving its potential for innovations and breakthroughs is electrical safety. AI can help to reduce human intervention and drastically reduce the factor of human error.

We propose Deterministic Sequencing of Exploration and Exploitation (DSEE) algorithm with interleaving exploration and exploitation epochs for model-based RL problems that aim to simultaneously learn the system model, i.e., a Markov decision process (MDP), and the associated optimal policy. During exploration, DSEE explores the environment and updates the estimates for expected reward and transition probabilities. During exploitation, the latest estimates of the expected reward and transition probabilities are used to obtain a robust policy with high probability. We design the lengths of the exploration and exploitation epochs such that the cumulative regret grows as a sub-linear function of time.

Metaheuristics are popularly used in various fields, and they have attracted much attention in the scientific and industrial communities. In recent years, the number of new metaheuristic names has been continuously growing. Generally, the inventors attribute the novelties of these new algorithms to inspirations from either biology, human behaviors, physics, or other phenomena. In addition, these new algorithms, compared against basic versions of other metaheuristics using classical benchmark problems without shift/rotation, show competitive performances. In this study, we exhaustively tabulate more than 500 metaheuristics. To comparatively evaluate the performance of the recent competitive variants and newly proposed metaheuristics, 11 newly proposed metaheuristics and 4 variants of established metaheuristics are comprehensively compared on the CEC2017 benchmark suite. In addition, whether these algorithms have a search bias to the center of the search space is investigated. The results show that the performance of the newly proposed EBCM (effective butterfly optimizer with covariance matrix adaptation) algorithm performs comparably to the 4 well performing variants of the established metaheuristics and possesses similar properties and behaviors, such as convergence, diversity, exploration and exploitation trade-offs, in many aspects. The performance of all 15 of the algorithms is likely to deteriorate due to certain transformations, while the 4 state-of-the-art metaheuristics are less affected by transformations such as the shifting of the global optimal point away from the center of the search space. It should be noted that, except EBCM, the other 10 new algorithms proposed mostly during 2019-2020 are inferior to the well performing 2017 variants of differential evolution and evolution strategy in terms of convergence speed and global search ability on CEC 2017 functions.

This paper presents an image-based visual servo control (IBVS) method for a first-person-view (FPV) quadrotor to conduct aggressive aerial tracking. There are three major challenges to maneuvering an underactuated vehicle using IBVS: (i) finding a visual feature representation that is robust to large rotations and is suited to be an optimization variable; (ii) keeping the target visible without sacrificing the robot's agility; and (iii) compensating for the rotational effects in the detected features. We propose a complete design framework to address these problems. First, we employ a rotation on $SO(3)$ to represent a spherical image feature on $S^{2}$ to gain singularity-free and second-order differentiable properties. To ensure target visibility, we formulate the IBVS as a nonlinear model predictive control (NMPC) problem with three constraints taken into account: the robot's physical limits, target visibility, and time-to-collision (TTC). Furthermore, we propose a novel attitude-compensation scheme to enable formulating the visibility constraint in the actual image plane instead of a virtual fix-orientation image plane. It guarantees that the visibility constraint is valid under large rotations. Extensive experimental results show that our method can track a fast-moving target stably and aggressively without the aid of a localization system.

The robustness of Text-to-SQL parsers against adversarial perturbations plays a crucial role in delivering highly reliable applications. Previous studies along this line primarily focused on perturbations in the natural language question side, neglecting the variability of tables. Motivated by this, we propose the Adversarial Table Perturbation (ATP) as a new attacking paradigm to measure the robustness of Text-to-SQL models. Following this proposition, we curate ADVETA, the first robustness evaluation benchmark featuring natural and realistic ATPs. All tested state-of-the-art models experience dramatic performance drops on ADVETA, revealing models' vulnerability in real-world practices. To defend against ATP, we build a systematic adversarial training example generation framework tailored for better contextualization of tabular data. Experiments show that our approach not only brings the best robustness improvement against table-side perturbations but also substantially empowers models against NL-side perturbations. We release our benchmark and code at: https://github.com/microsoft/ContextualSP.