Generative transformers have experienced rapid popularity growth in the computer vision community in synthesizing high-fidelity and high-resolution images. The best generative transformer models so far, however, still treat an image naively as a sequence of tokens, and decode an image sequentially following the raster scan ordering (i.e. line-by-line). We find this strategy neither optimal nor efficient. This paper proposes a novel image synthesis paradigm using a bidirectional transformer decoder, which we term MaskGIT. During training, MaskGIT learns to predict randomly masked tokens by attending to tokens in all directions. At inference time, the model begins with generating all tokens of an image simultaneously, and then refines the image iteratively conditioned on the previous generation. Our experiments demonstrate that MaskGIT significantly outperforms the state-of-the-art transformer model on the ImageNet dataset, and accelerates autoregressive decoding by up to 64x. Besides, we illustrate that MaskGIT can be easily extended to various image editing tasks, such as inpainting, extrapolation, and image manipulation.
Variational approximations to Gaussian processes (GPs) typically use a small set of inducing points to form a low-rank approximation to the covariance matrix. In this work, we instead exploit a sparse approximation of the precision matrix. We propose variational nearest neighbor Gaussian process (VNNGP), which introduces a prior that only retains correlations within K nearest-neighboring observations, thereby inducing sparse precision structure. Using the variational framework, VNNGP's objective can be factorized over both observations and inducing points, enabling stochastic optimization with a time complexity of O($K^3$). Hence, we can arbitrarily scale the inducing point size, even to the point of putting inducing points at every observed location. We compare VNNGP to other scalable GPs through various experiments, and demonstrate that VNNGP (1) can dramatically outperform low-rank methods, and (2) is less prone to overfitting than other nearest neighbor methods.
Among the seventeen Sustainable Development Goals (SDGs) proposed within the 2030 Agenda and adopted by all the United Nations member states, the Fifth SDG is a call for action to turn Gender Equality into a fundamental human right and an essential foundation for a better world. It includes the eradication of all types of violence against women. Within this context, the UC3M4Safety research team aims to develop Bindi. This is a cyber-physical system which includes embedded Artificial Intelligence algorithms, for user real-time monitoring towards the detection of affective states, with the ultimate goal of achieving the early detection of risk situations for women. On this basis, we make use of wearable affective computing including smart sensors, data encryption for secure and accurate collection of presumed crime evidence, as well as the remote connection to protecting agents. Towards the development of such system, the recordings of different laboratory and into-the-wild datasets are in process. These are contained within the UC3M4Safety Database. Thus, this paper presents and details the first release of WEMAC, a novel multi-modal dataset, which comprises a laboratory-based experiment for 47 women volunteers that were exposed to validated audio-visual stimuli to induce real emotions by using a virtual reality headset while physiological, speech signals and self-reports were acquired and collected. We believe this dataset will serve and assist research on multi-modal affective computing using physiological and speech information.
Semantic segmentation of point cloud usually relies on dense annotation that is exhausting and costly, so it attracts wide attention to investigate solutions for the weakly supervised scheme with only sparse points annotated. Existing works start from the given labels and propagate them to highly-related but unlabeled points, with the guidance of data, e.g. intra-point relation. However, it suffers from (i) the inefficient exploitation of data information, and (ii) the strong reliance on labels thus is easily suppressed when given much fewer annotations. Therefore, we propose a novel framework, PointMatch, that stands on both data and label, by applying consistency regularization to sufficiently probe information from data itself and leveraging weak labels as assistance at the same time. By doing so, meaningful information can be learned from both data and label for better representation learning, which also enables the model more robust to the extent of label sparsity. Simple yet effective, the proposed PointMatch achieves the state-of-the-art performance under various weakly-supervised schemes on both ScanNet-v2 and S3DIS datasets, especially on the settings with extremely sparse labels, e.g. surpassing SQN by 21.2% and 17.2% on the 0.01% and 0.1% setting of ScanNet-v2, respectively.
Instruction combiner (IC) is a critical compiler optimization pass, which replaces a sequence of instructions with an equivalent and optimized instruction sequence at basic block level. There can be thousands of instruction-combining patterns which need to be frequently updated as new coding idioms/applications and novel hardware evolve over time. This results in frequent updates to the IC optimization pass thereby incurring considerable human effort and high software maintenance costs. To mitigate these challenges associated with the traditional IC, we design and implement a Neural Instruction Combiner (NIC) and demonstrate its feasibility by integrating it into the standard LLVM compiler optimization pipeline. NIC leverages neural sequence-to-sequence (Seq2Seq) models for generating optimized encoded IR sequence from the unoptimized encoded IR sequence. To the best of our knowledge, ours is the first work demonstrating the feasibility of a neural instruction combiner built into a full-fledged compiler pipeline. Given the novelty of this task, we built a new dataset for training our NIC neural model. We show that NIC achieves exact match results percentage of 72% for optimized sequences as compared to traditional IC and neural machine translation metric Bleu precision score of 0.94, demonstrating its feasibility in a production compiler pipeline.
In this letter, we study the impact of the low-pass resistor-capacitor (RC) filter on radio frequency (RF) wireless power transfer (WPT). The RC filter influences both the RF bandwidth by removing the harmonics as well as the ripple voltage at the output of the rectifier. In particular, a large (small) RC time constant, reduces (increases) the ripple but decreases (enhances) the direct-current (DC) component. By following a Fourier series approach, we obtain closed-form expressions for the rectifier's output voltage, the RC filter's output as well as the DC voltage. Our analytical framework provides a complete characterization of the RC filter's impact on the WPT performance. We show that this complete and tractable analytical framework is suitable for the proper design of the RC filter in WPT systems.
Though construction robots have drawn attention in research and practice for decades, human-robot collaboration (HRC) remains important to conduct complex construction tasks. Considering its complexity and uniqueness, it is still unclear how HRC process will impact construction productivity. To this end, an agent-based (AB) multi-fidelity modeling approach is introduced to simulate and evaluate how HRC influences construction productivity. A high-fidelity model is first proposed for a scenario with one robot. Then, a low-fidelity model is established to extract key parameters that capture the inner relationship among scenarios. The multi-fidelity models work together to simulate complex scenarios. Simulation and experiements show that: 1) the proposed approach is feasible and flexible for simulation of complex HRC processes, and can cover multiple collaboration and interaction modes; 2) the influence of the supplement strategy is simple when there is only one robot, where lower Check Interval (CI) and higher Supplement Limit (SL) will improve productivity. But the influence becomes much more complicated when there are more robots due to the internal competition among robots for the limited time of workers; 3) the productivity per robot improves when there are more robots and workers, even if the human-robot ratio remains the same; 4) introducing proactive interaction between robots and workers could improve productivity significantly, up to 22% in our experiments, which further depends on the supplement strategy and the human-robot ratio. Overall, this research contributes an integrated approach to simulate and evaluate HRC's impacts on productivity as well as valuable insights on how to optimize HRC for better performance.
Toxicity on the Internet, such as hate speech, offenses towards particular users or groups of people, or the use of obscene words, is an acknowledged problem. However, there also exist other types of inappropriate messages which are usually not viewed as toxic, e.g. as they do not contain explicit offences. Such messages can contain covered toxicity or generalizations, incite harmful actions (crime, suicide, drug use), provoke "heated" discussions. Such messages are often related to particular sensitive topics, e.g. on politics, sexual minorities, social injustice which more often than other topics, e.g. cars or computing, yield toxic emotional reactions. At the same time, clearly not all messages within such flammable topics are inappropriate. Towards this end, in this work, we present two text collections labelled according to binary notion of inapropriateness and a multinomial notion of sensitive topic. Assuming that the notion of inappropriateness is common among people of the same culture, we base our approach on human intuitive understanding of what is not acceptable and harmful. To objectivise the notion of inappropriateness, we define it in a data-driven way though crowdsourcing. Namely we run a large-scale annotation study asking workers if a given chatbot textual statement could harm reputation of a company created it. Acceptably high values of inter-annotator agreement suggest that the notion of inappropriateness exists and can be uniformly understood by different people. To define the notion of sensitive topics in an objective way we use on guidelines suggested commonly by specialists of legal and PR department of a large public company as potentially harmful.
Tristructural isotropic (TRISO)-coated particle fuel is a robust nuclear fuel and determining its reliability is critical for the success of advanced nuclear technologies. However, TRISO failure probabilities are small and the associated computational models are expensive. We used coupled active learning, multifidelity modeling, and subset simulation to estimate the failure probabilities of TRISO fuels using several 1D and 2D models. With multifidelity modeling, we replaced expensive high-fidelity (HF) model evaluations with information fusion from two low-fidelity (LF) models. For the 1D TRISO models, we considered three multifidelity modeling strategies: only Kriging, Kriging LF prediction plus Kriging correction, and deep neural network (DNN) LF prediction plus Kriging correction. While the results across these multifidelity modeling strategies compared satisfactorily, strategies employing information fusion from two LF models consistently called the HF model least often. Next, for the 2D TRISO model, we considered two multifidelity modeling strategies: DNN LF prediction plus Kriging correction (data-driven) and 1D TRISO LF prediction plus Kriging correction (physics-based). The physics-based strategy, as expected, consistently required the fewest calls to the HF model. However, the data-driven strategy had a lower overall simulation time since the DNN predictions are instantaneous, and the 1D TRISO model requires a non-negligible simulation time.
Accurate and efficient pedestrian detection is crucial for the intelligent transportation system regarding pedestrian safety and mobility, e.g., Advanced Driver Assistance Systems, and smart pedestrian crosswalk systems. Among all pedestrian detection methods, vision-based detection method is demonstrated to be the most effective in previous studies. However, the existing vision-based pedestrian detection algorithms still have two limitations that restrict their implementations, those being real-time performance as well as the resistance to the impacts of environmental factors, e.g., low illumination conditions. To address these issues, this study proposes a lightweight Illumination and Temperature-aware Multispectral Network (IT-MN) for accurate and efficient pedestrian detection. The proposed IT-MN is an efficient one-stage detector. For accommodating the impacts of environmental factors and enhancing the sensing accuracy, thermal image data is fused by the proposed IT-MN with visual images to enrich useful information when visual image quality is limited. In addition, an innovative and effective late fusion strategy is also developed to optimize the image fusion performance. To make the proposed model implementable for edge computing, the model quantization is applied to reduce the model size by 75% while shortening the inference time significantly. The proposed algorithm is evaluated by comparing with the selected state-of-the-art algorithms using a public dataset collected by in-vehicle cameras. The results show that the proposed algorithm achieves a low miss rate and inference time at 14.19% and 0.03 seconds per image pair on GPU. Besides, the quantized IT-MN achieves an inference time of 0.21 seconds per image pair on the edge device, which also demonstrates the potentiality of deploying the proposed model on edge devices as a highly efficient pedestrian detection algorithm.