Modern-day surveillance systems perform person recognition using deep learning-based face verification networks. Most state-of-the-art facial verification systems are trained using visible spectrum images. But, acquiring images in the visible spectrum is impractical in scenarios of low-light and nighttime conditions, and often images are captured in an alternate domain such as the thermal infrared domain. Facial verification in thermal images is often performed after retrieving the corresponding visible domain images. This is a well-established problem often known as the Thermal-to-Visible (T2V) image translation. In this paper, we propose a Denoising Diffusion Probabilistic Model (DDPM) based solution for T2V translation specifically for facial images. During training, the model learns the conditional distribution of visible facial images given their corresponding thermal image through the diffusion process. During inference, the visible domain image is obtained by starting from Gaussian noise and performing denoising repeatedly. The existing inference process for DDPMs is stochastic and time-consuming. Hence, we propose a novel inference strategy for speeding up the inference time of DDPMs, specifically for the problem of T2V image translation. We achieve the state-of-the-art results on multiple datasets. The code and pretrained models are publically available at http://github.com/Nithin-GK/T2V-DDPM
Dataloaders, in charge of moving data from storage into GPUs while training machine learning models, might hold the key to drastically improving the performance of training jobs. Recent advances have shown promise not only by considerably decreasing training time but also by offering new features such as loading data from remote storage like S3. In this paper, we are the first to distinguish the dataloader as a separate component in the Deep Learning (DL) workflow and to outline its structure and features. Finally, we offer a comprehensive comparison of the different dataloading libraries available, their trade-offs in terms of functionality, usability, and performance and the insights derived from them.
Developing robot controllers in a simulated environment is advantageous but transferring the controllers to the target environment presents challenges, often referred to as the "sim-to-real gap". We present a method for continuous improvement of modeling and control after deploying the robot to a dynamically-changing target environment. We develop a differentiable physics simulation framework that performs online system identification and optimal control simultaneously, using the incoming observations from the target environment in real time. To ensure robust system identification against noisy observations, we devise an algorithm to assess the confidence of our estimated parameters, using numerical analysis of the dynamic equations. To ensure real-time optimal control, we adaptively schedule the optimization window in the future so that the optimized actions can be replenished faster than they are consumed, while staying as up-to-date with new sensor information as possible. The constant re-planning based on a constantly improved model allows the robot to swiftly adapt to the changing environment and utilize real-world data in the most sample-efficient way. Thanks to a fast differentiable physics simulator, the optimization for both system identification and control can be solved efficiently for robots operating in real time. We demonstrate our method on a set of examples in simulation and show that our results are favorable compared to baseline methods.
The problem of identifying the best arm among a collection of items having Gaussian rewards distribution is well understood when the variances are known. Despite its practical relevance for many applications, few works studied it for unknown variances. In this paper we introduce and analyze two approaches to deal with unknown variances, either by plugging in the empirical variance or by adapting the transportation costs. In order to calibrate our two stopping rules, we derive new time-uniform concentration inequalities, which are of independent interest. Then, we illustrate the theoretical and empirical performances of our two sampling rule wrappers on Track-and-Stop and on a Top Two algorithm. Moreover, by quantifying the impact on the sample complexity of not knowing the variances, we reveal that it is rather small.
Since the introduction of fifth-generation new radio (5G-NR) in Third Generation Partnership Project (3GPP) Release 15, swift progress has been made to evolve 5G with 3GPP Release 18 emerging. A critical aspect is the design of massive multiple-input multiple-output (MIMO) technology. In this line, this paper makes several important contributions: We provide a comprehensive overview of the evolution of standardized massive MIMO features from 3GPP Release 15 to 17 for both time/frequency-division duplex operation across bands FR-1 and FR-2. We analyze the progress on channel state information (CSI) frameworks, beam management frameworks and present enhancements for uplink CSI. We shed light on emerging 3GPP Release 18 problems requiring imminent attention. These include advanced codebook design and sounding reference signal design for coherent joint transmission (CJT) with multiple transmission/reception points (multi- TRPs). We discuss advancements in uplink demodulation reference signal design, enhancements for mobility to provide accurate CSI estimates, and unified transmission configuration indicator framework tailored for FR-2 bands. For each concept, we provide system level simulation results to highlight their performance benefits. Via field trials in an outdoor environment at Shanghai Jiaotong University, we demonstrate the gains of multi-TRP CJT relative to single TRP at 3.7 GHz.
This paper proposes a distributed Gaussian process regression (GPR) with over-the-air computation, termed AirComp GPR, for communication- and computation-efficient data analysis over wireless networks. GPR is a non-parametric regression method that can model the target flexibly. However, its computational complexity and communication efficiency tend to be significant as the number of data increases. AirComp GPR focuses on that product-of-experts-based GPR approximates the exact GPR by a sum of values reported from distributed nodes. We introduce AirComp for the training and prediction steps to allow the nodes to transmit their local computation results simultaneously; the communication strategies are presented, including distributed training based on perfect and statistical channel state information cases. Applying to a radio map construction task, we demonstrate that AirComp GPR speeds up the computation time while maintaining the communication cost in training constant regardless of the numbers of data and nodes.
Gaze cues play an important role in human communication and are used to coordinate turn-taking and joint attention, as well as to regulate intimacy. In order to have fluent conversations with people, social robots need to exhibit human-like gaze behavior. Previous Gaze Control Systems (GCS) in HRI have automated robot gaze using data-driven or heuristic approaches. However, these systems tend to be mainly reactive in nature. Planning the robot gaze ahead of time could help in achieving more realistic gaze behavior and better eye-head coordination. In this paper, we propose and implement a novel planning-based GCS. We evaluate our system in a comparative within-subjects user study (N=26) between a reactive system and our proposed system. The results show that the users preferred the proposed system and that it was significantly more interpretable and better at regulating intimacy.
Satellite images constitute a highly valuable and abundant resource for many real world applications. However, the labeled data needed to train most machine learning models are scarce and difficult to obtain. In this context, the current work investigates a fully unsupervised methodology that, given a temporal sequence of satellite images, creates a partition of the ground according to its semantic properties and their evolution over time. The sequences of images are translated into a grid of multivariate time series of embedded tiles. The embedding and the partitional clustering of these sequences of tiles are constructed in two iterative steps: In the first step, the embedding is able to extract the information of the sequences of tiles based on a geographical neighborhood, and the tiles are grouped into clusters. In the second step, the embedding is refined by using the neighborhood defined by the clusters, and the final clustering of the sequences of tiles is obtained. We illustrate the methodology by conducting the semantic clustering of a sequence of 20 satellite images of the region of Navarra (Spain). The results show that the clustering of multivariate time series is robust and contains trustful spatio-temporal semantic information about the region under study. We unveil the close connection that exists between the geographic and embedded spaces, and find out that the semantic properties attributed to these kinds of embeddings are fully exploited and even enhanced by the proposed clustering of time series.
Dense video understanding requires answering several questions such as who is doing what to whom, with what, how, why, and where. Recently, Video Situation Recognition (VidSitu) is framed as a task for structured prediction of multiple events, their relationships, and actions and various verb-role pairs attached to descriptive entities. This task poses several challenges in identifying, disambiguating, and co-referencing entities across multiple verb-role pairs, but also faces some challenges of evaluation. In this work, we propose the addition of spatio-temporal grounding as an essential component of the structured prediction task in a weakly supervised setting, and present a novel three stage Transformer model, VideoWhisperer, that is empowered to make joint predictions. In stage one, we learn contextualised embeddings for video features in parallel with key objects that appear in the video clips to enable fine-grained spatio-temporal reasoning. The second stage sees verb-role queries attend and pool information from object embeddings, localising answers to questions posed about the action. The final stage generates these answers as captions to describe each verb-role pair present in the video. Our model operates on a group of events (clips) simultaneously and predicts verbs, verb-role pairs, their nouns, and their grounding on-the-fly. When evaluated on a grounding-augmented version of the VidSitu dataset, we observe a large improvement in entity captioning accuracy, as well as the ability to localize verb-roles without grounding annotations at training time.
Recently, there has been tremendous interest in industry 4.0 infrastructure to address labor shortages in global supply chains. Deploying artificial intelligence-enabled robotic bin picking systems in real world has become particularly important for reducing labor demands and costs while increasing efficiency. To this end, artificial intelligence-enabled robotic bin picking systems may be used to automate bin picking, but may also cause expensive damage during an abnormal event such as a sensor failure. As such, reliability becomes a critical factor for translating artificial intelligence research to real world applications and products. In this paper, we propose a reliable vision system with MultiModal Redundancy (MMRNet) for tackling object detection and segmentation for robotic bin picking using data from different modalities. This is the first system that introduces the concept of multimodal redundancy to combat sensor failure issues during deployment. In particular, we realize the multimodal redundancy framework with a gate fusion module and dynamic ensemble learning. Finally, we present a new label-free multimodal consistency score that utilizes the output from all modalities to measure the overall system output reliability and uncertainty. Through experiments, we demonstrate that in an event of missing modality, our system provides a much more reliable performance compared to baseline models. We also demonstrate that our MC score is a more powerful reliability indicator for outputs during inference time where model generated confidence score are often over-confident.