Small Tasks Research Articles

ResFuseYOLOv4_Tiny: Enhancing detection accuracy for lightweight networks in infrared small object detection tasks

When deploying infrared target detection systems at the edge, one often encounters constraints on computational and storage resources. In such scenarios, lightweight networks prove to be a viable detection solution. Compared to large-scale deep networks, lightweight networks, after discarding redundant structures, often do not achieve satisfactory detection accuracy, especially in the context of small object detection tasks. This paper proposes ResFuseYOLOv4_Tiny, an improved lightweight network specifically designed for the effective detection of infrared small objects, particularly in resource-constrained scenarios. We extend the YOLOv4_Tiny neck network to enable efficient feature extraction. By integrating Res_head with residual structures and fusion-based feature reuse, our framework substantially enhances the capability to detect small objects by expanding the receptive field and effectively merging features from various receptive fields. Additionally, we introduce a drop and adaptive parameter-based attention mechanism called DCA, leveraging the inclusion of drop layers to effectively reduce information redundancy. Moreover, we replace the conventional CIoU loss function with our customized MSIoU, incorporating parameter m to adaptively adjust the loss weights in response to the influence of small target sizes. Experimental results conducted on synthetic and real infrared small object datasets respectively reveal a significant 14.47% and 11.28% improvement in detection accuracy. The proposed ResFuseYOLOv4_Tiny framework presents a viable solution for lightweight networks when both detection speed and accuracy are concurrently considered.

Small Object Navigation with Context Information

We introduce a novel framework designed to effectively address the object goal navigation task, specifically focusing on smaller daily household objects such as bowls or mugs. These diminutive objects present challenges to existing SLAM-based semantic mapping methods, as the object detection module employed in the mapping pipeline struggles to accurately detect them. To address this limitation, we propose to use a probabilistic semantic map. It is updated by a trained mapping module that incorporates contextual information to estimate the likelihood of object presence within the agent's current field of view. Subsequently, this probabilistic map guides the agent towards more promising areas for object search. Our experimental results demonstrate that the proposed method surpasses the SOTA approach by 26% in Small Object Navigation tasks.

Problems and prospects of developing an algorithm for flexible project management in the field of wholesale sales

The article is devoted to the study of the current state of problems and prospects for the development of an algorithm for flexible project management in the field of wholesale sales. Theoretical foundations of project and flexible management are revealed, the possibilities and ways of their integration are clarified. It is revealed that flexible management can become an instrumental basis for the reproduction of project management by providing radically new conditions for organizing project activities. Among the changes in the integration of project and flexible management, it is worth considering: organizing the activities of project teams that will act on the principles of co–organization and influence on the final result; application of a new delegation of authority scheme; redistribution and fragmentation of tasks into small tasks; rejection of phased implementation towards parallelization of project management; return to the previous stages of project activities in case of need to make changes; the establishment of new complementary projects to ensure a better outcome; rejection of downtime of individual groups in favor of a permanent distribution of tasks. These changes are positive effects in the implementation of projects based on flexible methodology. Based on the results of the study, the nature of the advantages and disadvantages of implementing flexible project management in the field of wholesale sales is demonstrated, conclusions are drawn about the possibilities and limitations of the development of appropriate algorithms and the nature of their testing.

UAV small target detection algorithm based on an improved YOLOv5s model

The targets of UAV target detection are usually small targets, and the backgrounds are complex. In this work, aiming at the problem that small targets are easy to be missed or misdetected during the UAV detection, an improved YOLOv5s_MSES target detection algorithm based on YOLOv5s is proposed. First of all, to solve the problem of UAV’s difficulty in detecting small targets, the detection layer is ameliorated into the small target detection layer STD, which makes the model more easily detect the small targets. Then, the multi-scale feature fusion module is added to improve the detection accuracy of the small targets. Furthermore, by combining multi-scale module and attention module, a new connection method is proposed to retain the large scale of feature information. Finally, in contrast with some existent methods, the experimental results of VisDrone2019 UAV target detection dataset show that our proposed YOLOv5s_MSES can achieve the better detection effect, and more effectively complete the small target detection task for UAV aerial photography images.

Let the loss impartial: a hierarchical unbiased loss for small object segmentation in high-resolution remote sensing images

ABSTRACT The progress in optical remote sensing technology presents both a possibility and challenge for small object segmentation task. However, the gap between human vision cognition and machine behavior still poses an inherent constrains to the interpretation of small but key objects in large-scale remote sensing scenes. This paper summarizes this gap as a bias of the machine against small object segmentation task, called scale-induced bias. The scale-induced bias causes the degradation in the performance of conventional remote sensing image segmentation methods. Therefore, this paper applies a straightforward but innovative insight to mitigate the scale-induced bias. Specifically, we propose a universal impartial loss, which leverages the hierarchical approach to alleviate two sub-problems separately. The pixel-level statistical methodology is applied to remove the bias between the background and small objects, and an emendation vector is introduced to alleviate the bias between small object categories. Extensive experiments explicitly manifest that our method is fully compatible with the existing segmentation structures, armed with the hierarchical unbiased loss, these structures will achieve satisfactory improvement. The proposed method is validated on two benchmark remote sensing image datasets, where it achieved a competitive performance and could narrow the gap between the human vision cognition and machine behavior.

Learning with Small Data: Subgraph Counting Queries

Deep Learning (DL) has been widely used in many applications, and its success is achieved with large training data. A key issue is how to provide a DL solution when there is no large training data to learn initially. In this paper, we explore a meta-learning approach for a specific problem, subgraph isomorphism counting, which is a fundamental problem in graph analysis to count the number of a given pattern graph, p, in a data graph, g, that matches p. There are various data graphs and pattern graphs. A subgraph isomorphism counting query is specified by a pair, (g, p). This problem is NP-hard and needs large training data to learn by DL in nature. We design a Gaussian Process (GP) model which combines Graph Neural Network with Bayesian nonparametric, and we train the GP by a meta-learning algorithm on a small set of training data. By meta-learning, we can obtain a generalized meta-model to better encode the information of data and pattern graphs and capture the prior of small tasks. With the meta-model learned, we handle a collection of pairs (g, p), as a task, where some pairs may be associated with the ground-truth, and some pairs are the queries to answer. There are two cases. One is there are some with ground-truth (few-shot), and one is there is none with ground-truth (zero-shot). We provide our solutions for both. In particular, for zero-shot, we propose a new data-driven approach to predict the count values. Note that zero-shot learning for our regression tasks is difficult, and there is no hands-on solution in the literature. We conducted extensive experimental studies to confirm that our approach is robust to model degeneration on small training data, and our meta-model can fast adapt to new queries by few-shot and zero-shot learning.

Improving the Performance of Delay-sensitive Multimedia Computation in Automotive Networks with DP-ERACOM using CloudSim Simulator

Abstract: We propose a Dynamic Priority-based Efficient Resource Allocation and Computing (DP-ERACOM) scheme for processing delay-sensitive multimedia computation in automotive networks. The proposed scheme breaks down each multimedia task into four smaller tasks and dynamically distributes resources based on the priority of the multimedia tasks. The three main processing and computing units in the proposed scheme are the load manager, compute cluster unit, and transmission unit. We evaluate the performance of the proposed scheme using CloudSim simulator. The results show that the proposed scheme can significantly improve the performance of delay-sensitive multimedia computation in automotive networks.

Predictive receding-horizon multi-robot task allocation applied to the mapping of direct normal irradiance in a thermosolar power plant

This article considers a robotic sensor network that measures the loss of irradiance in a thermosolar power plant due to moving clouds. To this end, a receding-horizon predictive algorithm is proposed for multi-robot task allocation. Despite the high nonlinearity of the problem, the experiments carried out varying the horizon size show that the proposed method has a good performance with small horizons and tasks moving in similar directions, outperforming a previously published approach based on genetic algorithms. Finally, realistic simulations performed on a solar plant implemented in Robot Operating System/Gazebo prove the feasibility of the proposed method and its potential to provide significant performance gains with a much lower investment than an equivalent fixed sensor network.

FireFly: A High-Throughput Hardware Accelerator for Spiking Neural Networks With Efficient DSP and Memory Optimization

Spiking neural networks (SNNs) have been widely used due to their strong biological interpretability and high energy efficiency. With the introduction of the backpropagation algorithm and surrogate gradient, the structure of spiking neural networks has become more complex, and the performance gap with artificial neural networks has gradually decreased. However, most SNN hardware implementations for field-programmable gate arrays (FPGAs) cannot meet arithmetic or memory efficiency requirements, which significantly restricts the development of SNNs. They do not delve into the arithmetic operations between the binary spikes and synaptic weights or assume unlimited on-chip RAM resources by using overly expensive devices on small tasks. To improve arithmetic efficiency, we analyze the neural dynamics of spiking neurons, generalize the SNN arithmetic operation to the multiplex-accumulate operation, and propose a high-performance implementation of such operation by utilizing the DSP48E2 hard block in Xilinx Ultrascale FPGAs. To improve memory efficiency, we design a memory system to enable efficient synaptic weights and membrane voltage memory access with reasonable on-chip RAM consumption. Combining the above two improvements, we propose an FPGA accelerator that can process spikes generated by the firing neuron on-the-fly (FireFly). FireFly is the first SNN accelerator that incorporates DSP optimization techniques into SNN synaptic operations. FireFly is implemented on several FPGA edge devices with limited resources but still guarantees a peak performance of 5.53TOP/s at 300MHz. As a lightweight accelerator, FireFly achieves the highest computational density efficiency compared with existing research using large FPGA devices.

Fostering pre-service teachers’ technology acceptance – does the type of engagement with tool-related information matter?

Pre-service teachers’ often suboptimal use of technology in teaching can be explained by low levels of technology acceptance. The present study aims to investigate how technology acceptance can be promoted. Based on the Technology Acceptance Model by Davis (1986), we hypothesized that encouraging pre-service teachers to constructively engage with rather than passively reading tool-related information should increase their assessments of the tool’s perceived usefulness, perceived ease of use, intention to use and actual use in lesson plans. In an experimental study, N = 53 pre-service teachers were either asked to read a blog post about the potential of a mind mapping tool (passive condition) or to work on small tasks covering the same information as the blog post (constructive condition). Finally, all participants were instructed to develop lesson plans. Contrary to our hypothesis, analyses of variance showed that passive engagement had stronger positive effects on technology acceptance than constructive engagement, i.e., reading a blog post significantly increased pre-service teachers’ perceived ease of use (partial η2 = .15) compared to working constructively on open-ended tasks (p < .01). Exploratory analyses indicated that deeper engagement with the tasks in the constructive condition was associated with lower technology acceptance (r = [–.37; –.27], p < .05). Nevertheless, both conditions yielded a significant increase in intention to use over time, indicating that engagement with information about a tool in general can foster pre-service teachers’ technology acceptance.

An Underwater Dense Small Object Detection Model Based on YOLOv5-CFDSDSE

Underwater target detection is a key technology in the process of exploring and developing the ocean. Because underwater targets are often very dense, mutually occluded, and affected by light, the detection objects are often unclear, and so, underwater target detection technology faces unique challenges. In order to improve the performance of underwater target detection, this paper proposed a new target detection model YOLOv5-FCDSDSE based on YOLOv5s. In this model, the CFnet (efficient fusion of C3 and FasterNet structure) structure was used to optimize the network structure of the YOLOv5, which improved the model’s accuracy while reducing the number of parameters. Then, Dyhead technology was adopted to achieve better scale perception, space perception, and task perception. In addition, the small object detection (SD) layer was added to combine feature information from different scales effectively, retain more detailed information, and improve the detection ability of small objects. Finally, the attention mechanism squeeze and excitation (SE) was introduced to enhance the feature extraction ability of the model. This paper used the self-made underwater small object dataset URPC_UODD for comparison and ablation experiments. The experimental results showed that the accuracy of the model proposed in this paper was better than the original YOLOv5s and other baseline models in the underwater dense small object detection task, and the number of parameters was also reduced compared to YOLOv5s. Therefore, YOLOv5-FCDSDSE was an innovative solution for underwater target detection tasks.

An Improving Faster-RCNN With Multi-Attention ResNet for Small Target Detection in Intelligent Autonomous Transport With 6G

Numerous object detection algorithms, such as Faster RCNN, YOLO and SSD, have been extensively applied to various fields. Both accuracy and speed of the algorithms have been significantly improved. However, as 6G technology develops, the detection effect for the small object detection task in intelligent autonomous transportation is not ideal. To strengthen the detection ability and performance of multiple scales, especially for small objects, this study proposed an object detection model based on multi-attention residual network (MA-ResNet). At first, residual network with spatial attention, channel attention, and self-attention were designed as MA-ResNet. Meanwhile, the dataset labels were smoothed. On this basis, the proposed MA-ResNet replaced the original feature extractor VGG-16 of Faster-RCNN. Different layers of MA-ResNet were extracted for feature pyramid construction. Moreover, the improved Faster-RCNN model for object detection based on MA-ResNet was formed. Furthermore, the effectiveness of the model was confirmed. The results demonstrate that MA-ResNet outperforms other feature extraction models with faster convergence speed, higher accuracy, and stronger small object classification accuracy. The improved Faster-RCNN model for object detection can effectively improve the network retrieval accuracy, performance and robustness, can exhibit satisfying adaptability for the targets of different scales in different scenarios such as vehicle identification, autonomous driving in intelligent autonomous transport system with 6G. Moreover, the study provides a certain reference for improving the effect of multiple scales, especially small object detection in intelligent transportation with 6G.

Evaluation of the EsteR Toolkit for COVID-19 Decision Support: Sensitivity Analysis and Usability Study.

During the COVID-19 pandemic, local health authorities were responsible for managing and reporting current cases in Germany. Since March 2020, employees had to contain the spread of COVID-19 by monitoring and contacting infected persons as well as tracing their contacts. In the EsteR project, we implemented existing and newly developed statistical models as decision support tools to assist in the work of the local health authorities. The main goal of this study was to validate the EsteR toolkit in two complementary ways: first, investigating the stability of the answers provided by our statistical tools regarding model parameters in the back end and, second, evaluating the usability and applicability of our web application in the front end by test users. For model stability assessment, a sensitivity analysis was carried out for all 5 developed statistical models. The default parameters of our models as well as the test ranges of the model parameters were based on a previous literature review on COVID-19 properties. The obtained answers resulting from different parameters were compared using dissimilarity metrics and visualized using contour plots. In addition, the parameter ranges of general model stability were identified. For the usability evaluation of the web application, cognitive walk-throughs and focus group interviews were conducted with 6 containment scouts located at 2 different local health authorities. They were first asked to complete small tasks with the tools and then express their general impressions of the web application. The simulation results showed that some statistical models were more sensitive to changes in their parameters than others. For each of the single-person use cases, we determined an area where the respective model could be rated as stable. In contrast, the results of the group use cases highly depended on the user inputs, and thus, no area of parameters with general model stability could be identified. We have also provided a detailed simulation report of the sensitivity analysis. In the user evaluation, the cognitive walk-throughs and focus group interviews revealed that the user interface needed to be simplified and more information was necessary as guidance. In general, the testers rated the web application as helpful, especially for new employees. This evaluation study allowed us to refine the EsteR toolkit. Using the sensitivity analysis, we identified suitable model parameters and analyzed how stable the statistical models were in terms of changes in their parameters. Furthermore, the front end of the web application was improved with the results of the conducted cognitive walk-throughs and focus group interviews regarding its user-friendliness.

AutoInit: Analytic Signal-Preserving Weight Initialization for Neural Networks

Neural networks require careful weight initialization to prevent signals from exploding or vanishing. Existing initialization schemes solve this problem in specific cases by assuming that the network has a certain activation function or topology. It is difficult to derive such weight initialization strategies, and modern architectures therefore often use these same initialization schemes even though their assumptions do not hold. This paper introduces AutoInit, a weight initialization algorithm that automatically adapts to different neural network architectures. By analytically tracking the mean and variance of signals as they propagate through the network, AutoInit appropriately scales the weights at each layer to avoid exploding or vanishing signals. Experiments demonstrate that AutoInit improves performance of convolutional, residual, and transformer networks across a range of activation function, dropout, weight decay, learning rate, and normalizer settings, and does so more reliably than data-dependent initialization methods. This flexibility allows AutoInit to initialize models for everything from small tabular tasks to large datasets such as ImageNet. Such generality turns out particularly useful in neural architecture search and in activation function discovery. In these settings, AutoInit initializes each candidate appropriately, making performance evaluations more accurate. AutoInit thus serves as an automatic configuration tool that makes design of new neural network architectures more robust. The AutoInit package provides a wrapper around TensorFlow models and is available at https://github.com/cognizant-ai-labs/autoinit.

ReBiDet: An Enhanced Ship Detection Model Utilizing ReDet and Bi-Directional Feature Fusion

To enhance ship detection accuracy in the presence of complex scenes and significant variations in object scales, this study introduces three enhancements to ReDet, resulting in a more powerful ship detection model called rotation-equivariant bidirectional feature fusion detector (ReBiDet). Firstly, the feature pyramid network (FPN) structure in ReDet is substituted with a rotation-equivariant bidirectional feature fusion feature pyramid network (ReBiFPN) to effectively capture and enrich multiscale feature information. Secondly, K-means clustering is utilized to group the aspect ratios of ground truth boxes in the dataset and adjust the anchor size settings accordingly. Lastly, the difficult positive reinforcement learning (DPRL) sampler is employed instead of the random sampler to address the scale imbalance issue between objects and backgrounds in the dataset, enabling the model to prioritize challenging positive examples. Through numerous experiments conducted on the HRSC2016 and DOTA remote sensing image datasets, the effectiveness of the proposed improvements in handling complex environments and small object detection tasks is validated. The ReBiDet model demonstrates state-of-the-art performance in remote sensing object detection tasks. Compared to the ReDet model and other advanced models, our ReBiDet achieves mAP improvements of 3.20, 0.42, and 1.16 on HRSC2016, DOTA-v1.0, and DOTA-v1.5, respectively, with only a slight increase of 0.82 million computational parameters.

An integrated convolutional neural network for classifying small pulmonary solid nodules.

Achieving accurate classification of benign and malignant pulmonary nodules is essential for treating some diseases. However, traditional typing methods have difficulty obtaining satisfactory results on small pulmonary solid nodules, mainly caused by two aspects: (1) noise interference from other tissue information; (2) missing features of small nodules caused by downsampling in traditional convolutional neural networks. To solve these problems, this paper proposes a new typing method to improve the diagnosis rate of small pulmonary solid nodules in CT images. Specifically, first, we introduce the Otsu thresholding algorithm to preprocess the data and filter the interference information. Then, to acquire more small nodule features, we add parallel radiomics to the 3D convolutional neural network. Radiomics can extract a large number of quantitative features from medical images. Finally, the classifier generated more accurate results by the visual and radiomic features. In the experiments, we tested the proposed method on multiple data sets, and the proposed method outperformed other methods in the small pulmonary solid nodule classification task. In addition, various groups of ablation experiments demonstrated that the Otsu thresholding algorithm and radiomics are helpful for the judgment of small nodules and proved that the Otsu thresholding algorithm is more flexible than the manual thresholding algorithm.

Audit Agility: Conceptual Framework

This study deals with the conceptual framework of agile audit, The agile methodology is especially well suited for complicated audits that call for a concentrated team and seasoned auditors to adhere to shorter audit cycles and speedier service delivery to its clients,. Agile is a method for reevaluating how teams approach projects or smaller tasks. Rapid adaptation to internal and external contexts is a key component of agility, which can enhance operational performance.

Wild Poppies by Haya Saleh

Reviewed by: Wild Poppies by Haya Saleh Natalie Berglind Saleh, Haya Wild Poppies; tr. from the Arabic by Marcia Lynx Qualey. Levine Querido, 2023 [192p] Trade ed. ISBN 9781646142019 $17.99 Reviewed from digital galleys R Gr. 5-8 Fifteen-year-old Omar is in charge of his family, including his sick mother, after his father was martyred in the Syrian civil war. At a Syrian refugee camp, Omar is the one who maintains order, while his twelve-year-old brother Sufyan is always getting into trouble and disappearing. When Sufyan becomes involved with a group called the Falcons of Truth, who pay him to complete small tasks and show up to their meetings declaiming “infidels,” finances start to look up, but the Falcons of Truth eventually kidnap Sufyan, and the brothers must find their way back to each other in life-or-death circumstances. Saleh’s prose, translated from Arabic, is elegant but direct, avoiding descriptions of violence without dulling the emotional impact of the tragedies in these brothers’ lives. Omar and Sufyan just want safety and reliable sources of food (and maybe some video games), and their alternating perspectives give readers two access points to a story that shines a light on the threats, both [End Page 335] present and in the future, that refugee children face. Media about Syrian refugees tends to focus on legislation about other countries accepting refugees rather than internally displaced refugees, and this book gives necessary context for kids who may be in the dark about the Syrian civil war. Copyright © 2023 The Board of Trustees of the University of Illinois

Two-Stage Auction Mechanism for Long-Term Participation in Crowdsourcing

Crowdsourcing has become an important tool to collect data for various artificial intelligence applications, and auction can be an effective way to allocate work and determine reward in a crowdsourcing platform. In this article, we focus on the crowdsourcing of small tasks such as image labeling and voice recording, where we face a number of challenges. First, workers have different limits on the amount of work they would be willing to do, and they may also misreport these limits in their bid for the work. Second, if the auction is repeated over time, unsuccessful workers may dropout of the system, reducing competition and diversity. To tackle these issues, we first extend the results of the celebrated Myerson's optimal auction mechanism for a single-parameter bid to the case where the bid consists of the unit cost of work, the maximum amount of work one is willing to do, and the actual work completed. We show that a simple payment mechanism is sufficient to ensure a dominant strategy from the workers, and that this dominant strategy is robust to the true utility function of the workers. Second, we propose a novel, flexible work allocation mechanism, which allows the requester to balance between cost efficiency and equality. While cost minimization is obviously important, encouraging equality in the allocation of work increases the diversity of the workforce as well as promotes a long-term participation on the crowdsourcing platform. Our main results are proved analytically and validated through simulations.

Road disease detection algorithm based on YOLOv5s-DSG

Automatic detection and classification of road damages are critical for the timely maintenance and repair of road surfaces. To address issues in road damage detection, such as single detection type, low detection efficiency, low-resolution detection objects, and difficulty in detecting small target features, this paper proposes an improved road damage detection algorithm YOLOv5s-DSG based on YOLOv5s. First, optimize the depth and width of the network structure to reduce the impact on road damage image detection performance. Second, the Ghost module replaces the traditional convolution to reduce the number of model parameters, making the model lightweight and improving the detection rate. Finally, the Space-to-depth-Conv module is introduced to adapt to low-resolution and small object detection tasks. Numerous experiments on datasets such as Road Damage Dataset 2022 demonstrate that the improved model’s average accuracy increased by 1.1% compared to the original model, FPS increased from 85 to 90, and the parameter quantity decreased by 21.7%. It effectively alleviates problems in recognizing small targets. Compared to existing algorithms, it has significant advantages in road damage detection and classification.