The artistic style of a painting is a rich descriptor that reveals both visual and deep intrinsic knowledge about how an artist uniquely portrays and expresses their creative vision. Accurate categorization of paintings across different artistic movements and styles is critical for large-scale indexing of art databases. However, the automatic extraction and recognition of these highly dense artistic features has received little to no attention in the field of computer vision research. In this paper, we investigate the use of deep self-supervised learning methods to solve the problem of recognizing complex artistic styles with high intra-class and low inter-class variation. Further, we outperform existing approaches by almost 20% on a highly class imbalanced WikiArt dataset with 27 art categories. To achieve this, we train the EnAET semi-supervised learning model (Wang et al., 2019) with limited annotated data samples and supplement it with self-supervised representations learned from an ensemble of spatial and non-spatial transformations.

Can we learn how to explore unknown spaces efficiently? To answer this question, we study the problem of Online Graph Exploration, the online version of the Traveling Salesperson Problem. We reformulate graph exploration as a reinforcement learning problem and apply Direct Future Prediction (Dosovitskiy and Koltun, 2016) to solve it. As the graph is discovered online, the corresponding Markov Decision Process entails a dynamic state space, namely the observable graph and a dynamic action space, namely the nodes forming the graph's frontier. To the best of our knowledge, this is the first attempt to solve online graph exploration in a data-driven way. We conduct experiments on six data sets of procedurally generated graphs and three real city road networks. We demonstrate that our agent can learn strategies superior to many well known graph traversal algorithms, confirming that exploration can be learned.

In this paper, we introduce a novel method to pseudo-label unlabelled images and train an Auto-Encoder to classify them in a self-supervised manner that allows for a high accuracy and consistency across several datasets. The proposed method consists of first applying a randomly sampled set of data augmentation transformations to each training image. As a result, each initial image can be considered as a pseudo-label to its corresponding augmented ones. Then, an Auto-Encoder is used to learn the mapping between each set of the augmented images and its corresponding pseudo-label. Furthermore, the perceptual loss is employed to take into consideration the existing dependencies between the pixels in the same neighbourhood of an image. This combination encourages the encoder to output richer encodings that are highly informative of the input's class. Consequently, the Auto-Encoder's performance on unsupervised image classification is improved both in termes of stability and accuracy becoming more uniform and more consistent across all tested datasets. Previous state-of-the-art accuracy on the MNIST, CIFAR-10 and SVHN datasets is improved by 0.3\%, 3.11\% and 9.21\% respectively.

In this work, we propose TediGAN, a novel framework for multi-modal image generation and manipulation with textual descriptions. The proposed method consists of three components: StyleGAN inversion module, visual-linguistic similarity learning, and instance-level optimization. The inversion module is to train an image encoder to map real images to the latent space of a well-trained StyleGAN. The visual-linguistic similarity is to learn the text-image matching by mapping the image and text into a common embedding space. The instance-level optimization is for identity preservation in manipulation. Our model can provide the lowest effect guarantee, and produce diverse and high-quality images with an unprecedented resolution at 1024. Using a control mechanism based on style-mixing, our TediGAN inherently supports image synthesis with multi-modal inputs, such as sketches or semantic labels with or without instance (text or real image) guidance. To facilitate text-guided multi-modal synthesis, we propose the Multi-Modal CelebA-HQ, a large-scale dataset consisting of real face images and corresponding semantic segmentation map, sketch, and textual descriptions. Extensive experiments on the introduced dataset demonstrate the superior performance of our proposed method. Code and data are available at https://github.com/weihaox/TediGAN.

Performing simple household tasks based on language directives is very natural to humans, yet it remains an open challenge for an AI agent. Recently, an `interactive instruction following' task has been proposed to foster research in reasoning over long instruction sequences that requires object interactions in a simulated environment. It involves solving open problems in vision, language and navigation literature at each step. To address this multifaceted problem, we propose a modular architecture that decouples the task into visual perception and action policy, and name it as MOCA, a Modular Object-Centric Approach. We evaluate our method on the ALFRED benchmark and empirically validate that it outperforms prior arts by significant margins in all metrics with good generalization performance (high success rate in unseen environments). Our code is available at https://github.com/gistvision/moca.

In the last years, AI safety gained international recognition in the light of heterogeneous safety-critical and ethical issues that risk overshadowing the broad beneficial impacts of AI. In this context, the implementation of AI observatory endeavors represents one key research direction. This paper motivates the need for an inherently transdisciplinary AI observatory approach integrating diverse retrospective and counterfactual views. We delineate aims and limitations while providing hands-on-advice utilizing concrete practical examples. Distinguishing between unintentionally and intentionally triggered AI risks with diverse socio-psycho-technological impacts, we exemplify a retrospective descriptive analysis followed by a retrospective counterfactual risk analysis. Building on these AI observatory tools, we present near-term transdisciplinary guidelines for AI safety. As further contribution, we discuss differentiated and tailored long-term directions through the lens of two disparate modern AI safety paradigms. For simplicity, we refer to these two different paradigms with the terms artificial stupidity (AS) and eternal creativity (EC) respectively. While both AS and EC acknowledge the need for a hybrid cognitive-affective approach to AI safety and overlap with regard to many short-term considerations, they differ fundamentally in the nature of multiple envisaged long-term solution patterns. By compiling relevant underlying contradistinctions, we aim to provide future-oriented incentives for constructive dialectics in practical and theoretical AI safety research.

Establishing a theoretical analysis that explains why deep learning can outperform shallow learning such as kernel methods is one of the biggest issues in the deep learning literature. Towards answering this question, we evaluate excess risk of a deep learning estimator trained by a noisy gradient descent with ridge regularization on a mildly overparameterized neural network, and discuss its superiority to a class of linear estimators that includes neural tangent kernel approach, random feature model, other kernel methods, k-NN estimator and so on. We consider a teacher-student regression model, and eventually show that any linear estimator can be outperformed by deep learning in a sense of the minimax optimal rate especially for a high dimension setting. The obtained excess bounds are so-called fast learning rate which is faster thanO(1/ n) that is obtained by usual Rademacher complexity analysis. This discrepancy is induced by the non-convex geometry of the model and the noisy gradient descent used for neural network training provably reaches a near global optimal solution even though the loss landscape is highly non-convex. Although the noisy gradient descent does not employ any explicit or implicit sparsity inducing regularization, it shows a preferable generalization performance that dominates linear estimators. In the deep learning theory literature, clarifying the mechanism by which deep learning can outperform shallow approaches has been gathering most attention for a long time.

I first came across the Kalman filter during my undergraduate studies when I took the navigation systems class. It was the last lecture, and the professor said it is out of the course syllabus, but if someone will deal with real-time applications, he is expected to meet it again. He was right, and I kept studying for a master's degree in the field of Guidance, Control, and Navigation (GCN) at the Aerospace Engineering Faculty of the Technion. I came across the Kalman filter again, where I used it to filter noisy measurements from various sensors during real-time navigation problems. Later on, I used different Kalman filter extensions while exploring solutions for real-life problems, such as Extended Kalman Filter, Iterated EKF, etc. Today, I am pursuing my Ph.D. degree at the University of Haifa, and I use the Kalman filter aside from machine learning to solve challenging navigation problems.

Whether robots are improving the efficiency of industries, helping with medical surgeries or enabling Earth and space exploration, these devices are increasingly attracting the attention of enterprises and their software developers. For companies interested in further developing these devices, Amazon Web Services Inc. is boosting its RoboMaker -- its cloud solution for robotic developers -- with new industrial machine learning services, announced this week during the virtual AWS re:Invent event. "We continue to see the story of how processing is moving to the edge and cloud services are augmenting that processing at the edge with unique and new services," said Roger Barga (pictured), general manager of AWS robotics and autonomous services at AWS. "Andy [Jassy, chief executive of AWS] talked about five new industrial machine learning services yesterday, which are very relevant to exactly what we're trying to do with AWS RoboMaker." They discussed how new ML services improve the AWS RoboMaker, the importance of testing in simulation to enable dynamic robots, and some interesting use cases.

Social media popularity and importance is on the increase, due to people using it for various types of social interaction across multiple channels. This social interaction by online users includes submission of feedback, opinions and recommendations about various individuals, entities, topics, and events. This systematic review focuses on the evolving research area of Social Opinion Mining, tasked with the identification of multiple opinion dimensions, such as subjectivity, sentiment polarity, emotion, affect, sarcasm and irony, from user-generated content represented across multiple social media platforms and in various media formats, like text, image, video and audio. Therefore, through Social Opinion Mining, natural language can be understood in terms of the different opinion dimensions, as expressed by humans. This contributes towards the evolution of Artificial Intelligence, which in turn helps the advancement of several real-world use cases, such as customer service and decision making. A thorough systematic review was carried out on Social Opinion Mining research which totals 485 studies and spans a period of twelve years between 2007 and 2018. The in-depth analysis focuses on the social media platforms, techniques, social datasets, language, modality, tools and technologies, natural language processing tasks and other aspects derived from the published studies. Such multi-source information fusion plays a fundamental role in mining of people's social opinions from social media platforms. These can be utilised in many application areas, ranging from marketing, advertising and sales for product/service management, and in multiple domains and industries, such as politics, technology, finance, healthcare, sports and government. Future research directions are presented, whereas further research and development has the potential of leaving a wider academic and societal impact.