Identifying relations between objects is central to understanding the scene. While several works have been proposed for relation modeling in the image domain, there have been many constraints in the video domain due to challenging dynamics of spatio-temporal interactions (e.g., Between which objects are there an interaction? When do relations occur and end?). To date, two representative methods have been proposed to tackle Video Visual Relation Detection (VidVRD): segment-based and window-based. We first point out the limitations these two methods have and propose Temporal Span Proposal Network (TSPN), a novel method with two advantages in terms of efficiency and effectiveness. 1) TSPN tells what to look: it sparsifies relation search space by scoring relationness (i.e., confidence score for the existence of a relation between pair of objects) of object pair. 2) TSPN tells when to look: it leverages the full video context to simultaneously predict the temporal span and categories of the entire relations. TSPN demonstrates its effectiveness by achieving new state-of-the-art by a significant margin on two VidVRD benchmarks (ImageNet-VidVDR and VidOR) while also showing lower time complexity than existing methods - in particular, twice as efficient as a popular segment-based approach.
We propose Banker-OMD, a novel framework generalizing the classical Online Mirror Descent (OMD) technique in online learning algorithm design. Banker-OMD allows algorithms to robustly handle delayed feedback, and offers a general methodology for achieving $\tilde{O}(\sqrt{T} + \sqrt{D})$-style regret bounds in various delayed-feedback online learning tasks, where $T$ is the time horizon length and $D$ is the total feedback delay. We demonstrate the power of Banker-OMD with applications to three important bandit scenarios with delayed feedback, including delayed adversarial Multi-armed bandits (MAB), delayed adversarial linear bandits, and a novel delayed best-of-both-worlds MAB setting. Banker-OMD achieves nearly-optimal performance in all the three settings. In particular, it leads to the first delayed adversarial linear bandit algorithm achieving $\tilde{O}(\text{poly}(n)(\sqrt{T} + \sqrt{D}))$ regret.
The ability to plan into the future while utilizing only raw high-dimensional observations, such as images, can provide autonomous agents with broad capabilities. Visual model-based reinforcement learning (RL) methods that plan future actions directly have shown impressive results on tasks that require only short-horizon reasoning, however, these methods struggle on temporally extended tasks. We argue that it is easier to solve long-horizon tasks by planning sequences of states rather than just actions, as the effects of actions greatly compound over time and are harder to optimize. To achieve this, we draw on the idea of collocation, which has shown good results on long-horizon tasks in optimal control literature, and adapt it to the image-based setting by utilizing learned latent state space models. The resulting latent collocation method (LatCo) optimizes trajectories of latent states, which improves over previously proposed shooting methods for visual model-based RL on tasks with sparse rewards and long-term goals. Videos and code at https://orybkin.github.io/latco/.
Autonomous systems are becoming inherently ubiquitous with the advancements of computing and communication solutions enabling low-latency offloading and real-time collaboration of distributed devices. Decentralized technologies with blockchain and distributed ledger technologies (DLTs) are playing a key role. At the same time, advances in deep learning (DL) have significantly raised the degree of autonomy and level of intelligence of robotic and autonomous systems. While these technological revolutions were taking place, raising concerns in terms of data security and end-user privacy has become an inescapable research consideration. Federated learning (FL) is a promising solution to privacy-preserving DL at the edge, with an inherently distributed nature by learning on isolated data islands and communicating only model updates. However, FL by itself does not provide the levels of security and robustness required by today's standards in distributed autonomous systems. This survey covers applications of FL to autonomous robots, analyzes the role of DLT and FL for these systems, and introduces the key background concepts and considerations in current research.
High-quality labeled datasets play a crucial role in fueling the development of machine learning (ML), and in particular the development of deep learning (DL). However, since the emergence of the ImageNet dataset and the AlexNet model in 2012, the size of new open-source labeled vision datasets has remained roughly constant. Consequently, only a minority of publications in the computer vision community tackle supervised learning on datasets that are orders of magnitude larger than Imagenet. In this paper, we survey computer vision research domains that study the effects of such large datasets on model performance across different vision tasks. We summarize the community's current understanding of those effects, and highlight some open questions related to training with massive datasets. In particular, we tackle: (a) The largest datasets currently used in computer vision research and the interesting takeaways from training on such datasets; (b) The effectiveness of pre-training on large datasets; (c) Recent advancements and hurdles facing synthetic datasets; (d) An overview of double descent and sample non-monotonicity phenomena; and finally, (e) A brief discussion of lifelong/continual learning and how it fares compared to learning from huge labeled datasets in an offline setting. Overall, our findings are that research on optimization for deep learning focuses on perfecting the training routine and thus making DL models less data hungry, while research on synthetic datasets aims to offset the cost of data labeling. However, for the time being, acquiring non-synthetic labeled data remains indispensable to boost performance.
Simulation has recently become key for deep reinforcement learning to safely and efficiently acquire general and complex control policies from visual and proprioceptive inputs. Tactile information is not usually considered despite its direct relation to environment interaction. In this work, we present a suite of simulated environments tailored towards tactile robotics and reinforcement learning. A simple and fast method of simulating optical tactile sensors is provided, where high-resolution contact geometry is represented as depth images. Proximal Policy Optimisation (PPO) is used to learn successful policies across all considered tasks. A data-driven approach enables translation of the current state of a real tactile sensor to corresponding simulated depth images. This policy is implemented within a real-time control loop on a physical robot to demonstrate zero-shot sim-to-real policy transfer on several physically-interactive tasks requiring a sense of touch.
Magnetic Particle Imaging (MPI) is a promising tracer-based, functional medical imaging technique which measures the non-linear response of superparamagnetic iron oxide nanoparticles (SPION) to a dynamic magnetic field. For image reconstruction, system matrices from time-consuming calibration scans are used predominantly. Finding modeled forward operators for magnetic particle imaging, which are able to compete with measured matrices in practice, is an ongoing topic of research. The existing models for magnetic particle imaging are by design not suitable for dynamic tracer concentrations. Neither modeled nor measured system matrices account for changes in the concentration during a single scanning cycle. In this paper we present a new MPI forward model for dynamic concentrations. A standard model will be introduced briefly, followed by the changes due to the dynamic behavior of the tracer concentration. Furthermore, the relevance of this new extended model is examined by investigating the influence of the extension and example reconstructions with the new and the standard model.
Autoencoders and generative neural network models have recently gained popularity in fluid mechanics due to their spontaneity and low processing time instead of high fidelity CFD simulations. Auto encoders are used as model order reduction tools in applications of fluid mechanics by compressing input high-dimensional data using an encoder to map the input space into a lower-dimensional latent space. Whereas, generative models such as Variational Auto-encoders (VAEs) and Generative Adversarial Networks (GANs) are proving to be effective in generating solutions to chaotic models with high 'randomness' such as turbulent flows. In this study, forced isotropic turbulence flow is generated by parameterizing into some basic statistical characteristics. The models trained on pre-simulated data from dependencies on these characteristics and the flow generation is then affected by varying these parameters. The latent vectors pushed along the generator models like the decoders and generators contain independent entries which can be used to create different outputs with similar properties. The use of neural network-based architecture removes the need for dependency on the classical mesh-based Navier-Stoke equation estimation which is prominent in many CFD softwares.
Determining the dynamics of the expectation values for operators acting on a quantum many-body (QMB) system is a challenging task. Matrix product states (MPS) have traditionally been the "go-to" models for these systems because calculating expectation values in this representation can be done with relative simplicity and high accuracy. However, such calculations can become computationally costly when extended to long times. Here, we present a solution for efficiently extending the computation of expectation values to long time intervals. We utilize a multi-layer perceptron (MLP) model as a tool for regression on MPS expectation values calculated within the regime of short time intervals. With this model, the computational cost of generating long-time dynamics is significantly reduced, while maintaining a high accuracy. These results are demonstrated with operators relevant to quantum spin models in one spatial dimension.
Approximating quantiles and distributions over streaming data has been studied for roughly two decades now. Recently, Karnin, Lang, and Liberty proposed the first asymptotically optimal algorithm for doing so. This manuscript complements their theoretical result by providing a practical variants of their algorithm with improved constants. For a given sketch size, our techniques provably reduce the upper bound on the sketch error by a factor of two. These improvements are verified experimentally. Our modified quantile sketch improves the latency as well by reducing the worst case update time from $O(1/\varepsilon)$ down to $O(\log (1/\varepsilon))$. We also suggest two algorithms for weighted item streams which offer improved asymptotic update times compared to na\"ive extensions. Finally, we provide a specialized data structure for these sketches which reduces both their memory footprints and update times.