This paper proposes a novel pixel interval down-sampling network (PID-Net) for dense tiny object (yeast cells) counting tasks with higher accuracy. The PID-Net is an end-to-end convolutional neural network (CNN) model with an encoder--decoder architecture. The pixel interval down-sampling operations are concatenated with max-pooling operations to combine the sparse and dense features. This addresses the limitation of contour conglutination of dense objects while counting. The evaluation was conducted using classical segmentation metrics (the Dice, Jaccard and Hausdorff distance) as well as counting metrics. The experimental results show that the proposed PID-Net had the best performance and potential for dense tiny object counting tasks, which achieved 96.97\% counting accuracy on the dataset with 2448 yeast cell images. By comparing with the state-of-the-art approaches, such as Attention U-Net, Swin U-Net and Trans U-Net, the proposed PID-Net can segment dense tiny objects with clearer boundaries and fewer incorrect debris, which shows the great potential of PID-Net in the task of accurate counting.

Modern neural networks use building blocks such as convolutions that are equivariant to arbitrary 2D translations. However, these vanilla blocks are not equivariant to arbitrary 3D translations in the projective manifold. Even then, all monocular 3D detectors use vanilla blocks to obtain the 3D coordinates, a task for which the vanilla blocks are not designed for. This paper takes the first step towards convolutions equivariant to arbitrary 3D translations in the projective manifold. Since the depth is the hardest to estimate for monocular detection, this paper proposes Depth EquiVarIAnt NeTwork (DEVIANT) built with existing scale equivariant steerable blocks. As a result, DEVIANT is equivariant to the depth translations in the projective manifold whereas vanilla networks are not. The additional depth equivariance forces the DEVIANT to learn consistent depth estimates, and therefore, DEVIANT achieves state-of-the-art monocular 3D detection results on KITTI and Waymo datasets in the image-only category and performs competitively to methods using extra information. Moreover, DEVIANT works better than vanilla networks in cross-dataset evaluation.

Birds-eye-view (BEV) semantic segmentation is critical for autonomous driving for its powerful spatial representation ability. It is challenging to estimate the BEV semantic maps from monocular images due to the spatial gap, since it is implicitly required to realize both the perspective-to-BEV transformation and segmentation. We present a novel two-stage Geometry Prior-based Transformation framework named GitNet, consisting of (i) the geometry-guided pre-alignment and (ii) ray-based transformer. In the first stage, we decouple the BEV segmentation into the perspective image segmentation and geometric prior-based mapping, with explicit supervision by projecting the BEV semantic labels onto the image plane to learn visibility-aware features and learnable geometry to translate into BEV space. Second, the pre-aligned coarse BEV features are further deformed by ray-based transformers to take visibility knowledge into account. GitNet achieves the leading performance on the challenging nuScenes and Argoverse Datasets.

In this work we introduce KERNELIZED TRANSFORMER, a generic, scalable, data driven framework for learning the kernel function in Transformers. Our framework approximates the Transformer kernel as a dot product between spectral feature maps and learns the kernel by learning the spectral distribution. This not only helps in learning a generic kernel end-to-end, but also reduces the time and space complexity of Transformers from quadratic to linear. We show that KERNELIZED TRANSFORMERS achieve performance comparable to existing efficient Transformer architectures, both in terms of accuracy as well as computational efficiency. Our study also demonstrates that the choice of the kernel has a substantial impact on performance, and kernel learning variants are competitive alternatives to fixed kernel Transformers, both in long as well as short sequence tasks.

BERLIN, July 20, 2022 (GLOBE NEWSWIRE) -- The Global Artificial Intelligence in Accounting Market size accounted for USD 1,511 Million in 2021 and is estimated to reach USD 53,893 Million by 2030. The rising need for faster and more accurate accounting in private and public firms is the recent artificial intelligence in accounting market trend that fuels the demand. In addition, the growing number of financial data is anticipated to expand artificial intelligence in accounting market revenue. Integrating AI into accounting can also improve accuracy while decreasing human error. This can further optimize the accounting process because reducing errors means spending less time discovering, tracking down, and correcting errors.

The scarcity of high-quality annotated medical imaging datasets is a major problem that collides with machine learning applications in the field of medical imaging analysis and impedes its advancement. Self-supervised learning is a recent training paradigm that enables learning robust representations without the need for human annotation which can be considered an effective solution for the scarcity of annotated medical data. This article reviews the state-of-the-art research directions in self-supervised learning approaches for image data with a concentration on their applications in the field of medical imaging analysis. The article covers a set of the most recent self-supervised learning methods from the computer vision field as they are applicable to the medical imaging analysis and categorize them as predictive, generative, and contrastive approaches. Moreover, the article covers 40 of the most recent research papers in the field of self-supervised learning in medical imaging analysis aiming at shedding the light on the recent innovation in the field. Finally, the article concludes with possible future research directions in the field.

In the RoboCup Small Size League (SSL), teams are encouraged to propose solutions for executing basic soccer tasks inside the SSL field using only embedded sensing information. Thus, this work proposes an embedded monocular vision approach for detecting objects and estimating relative positions inside the soccer field. Prior knowledge from the environment is exploited by assuming objects lay on the ground, and the onboard camera has its position fixed on the robot. We implemented the proposed method on an NVIDIA Jetson Nano and employed SSD MobileNet v2 for 2D Object Detection with TensorRT optimization, detecting balls, robots, and goals with distances up to 3.5 meters. Ball localization evaluation shows that the proposed solution overcomes the currently used SSL vision system for positions closer than 1 meter to the onboard camera with a Root Mean Square Error of 14.37 millimeters. In addition, the proposed method achieves real-time performance with an average processing speed of 30 frames per second.

Teleoperation is a widely adopted strategy to control robotic manipulators executing complex tasks that require highly dexterous movements and critical high-level intelligence. Classical teleoperation schemes are based on either joystick control, or on more intuitive interfaces which map directly the user arm motions into one robot arm's motions. These approaches have limits when the execution of a given task requires reconfigurable multiple robotic arm systems. Indeed, the simultaneous teleoperation of two or more robot arms could extend the workspace of the manipulation cell, or increase its total payload, or afford other advantages. In different phases of a reconfigurable multi-arm system, each robot could act as an independent arm, or as one of a pair of cooperating arms, or as one of the fingers of a virtual, large robot hand. This manuscript proposes a novel telemanipulation framework that enables both the individual and combined control of any number of robotic arms. Thanks to the designed control architecture, the human operator can intuitively choose the proposed control modalities and the manipulators that make the task convenient to execute through the user interface. Moreover, through the tele-impedance paradigm, the system can address complex tasks that require physical interaction by letting the robot mimic the arm impedance and position references of the human operator. The proposed framework is validated with 8 subjects controlling 4 Franka Emika Panda robots with 7-DoFs to execute a telemanipulation task. Qualitative results of the experiments show us the promising applicability of our framework.

Edge computing enables smart IoT-based systems via concurrent and continuous execution of latency-sensitive machine learning (ML) applications. These edge-based machine learning systems are often battery-powered (i.e., energy-limited). They use heterogeneous resources with diverse computing performance (e.g., CPU, GPU, and/or FPGAs) to fulfill the latency constraints of ML applications. The challenge is to allocate user requests for different ML applications on the Heterogeneous Edge Computing Systems (HEC) with respect to both the energy and latency constraints of these systems. To this end, we study and analyze resource allocation solutions that can increase the on-time task completion rate while considering the energy constraint. Importantly, we investigate edge-friendly (lightweight) multi-objective mapping heuristics that do not become biased toward a particular application type to achieve the objectives; instead, the heuristics consider "fairness" across the concurrent ML applications in their mapping decisions. Performance evaluations demonstrate that the proposed heuristic outperforms widely-used heuristics in heterogeneous systems in terms of the latency and energy objectives, particularly, at low to moderate request arrival rates. We observed 8.9% improvement in on-time task completion rate and 12.6% in energy-saving without imposing any significant overhead on the edge system.

Examples can be found in all areas of engineering and science, for instance plant breeding (Hunter & McClosky, 2016), aircraft maintenance (Mattila & Virtanen, 2014) or electric network planning (Dutrieux et al., 2015b). In this work, we choose to focus on Bayesian optimization algorithms, which use probabilistic models to make predictions about the functions to be optimized. One of the classical algorithms for Bayesian deterministic multi-objective optimization is the ParEGO algorithm (Knowles, 2006). It relies on a scalarization approach to extend the very popular single-objective Efficient Global Optimization (EGO) algorithm (Jones et al., 1998), based on the Expected Improvement (EI) criterion. Another scalarization approach, called multi-attribute Knowledge Gradient (Astudillo & Frazier, 2017), uses the Knowledge Gradient (KG) criterion instead of the EI criterion.