Small Tasks Research Articles

Cellfare: Delivering Self-Targeted Social Protection Using Mobile Phones

This article proposes a new form of self-targeted social protection scheme: beneficiaries carry out a series of small tasks on their mobile phones, each linked to a small payment. Key advantages over traditional public works include potentially large reductions in leakage, costs, and delays. The proposed scheme may also be suitable to wider demographics as it does not require physical labour and can be availed from home. A prototype implementation of a ‘cellfare’ scheme was tested in rural India, and 42 participants with experience of the Mahatma Gandhi National Rural Employment Guarantee Act, a large Indian public works programme, favourably compared the proposed scheme to the existing one.

SOD-YOLO: A lightweight small object detection framework

Currently, lightweight small object detection algorithms for unmanned aerial vehicles (UAVs) often employ group convolutions, resulting in high Memory Access Cost (MAC) and rendering them unsuitable for edge devices that rely on parallel computing. To address this issue, we propose the SOD-YOLO model based on YOLOv7, which incorporates a DSDM-LFIM backbone network and includes a small object detection branch. The DSDM-LFIM backbone network, which combines Deep-Shallow Downsampling Modules (DSD Modules) and Lightweight Feature Integration Modules (LFI Modules), avoids excessive use of group convolutions and element-wise operations. The DSD Module focuses on extracting both deep and shallow features from feature maps using fewer parameters to obtain richer feature representations. The LFI Module, is a dual-branch feature integration module designed to consolidate feature information. Experimental results demonstrate that the SOD-YOLO model achieves an AP50 of 50.7% and a FPS of 72.5 on the VisDrone validation set. Compared to YOLOv7, our model reduces computational costs by 20.25% and decreases the number of parameters by 17.89%. After scaling the number of channels in the model, it achieves an AP50 of 33.4% with an inference time of 27.3ms on the Atlas 200I DK A2. These experimental results indicate that the SOD-YOLO model can effectively perform small object detection tasks in a large number of aerial images captured by UAVs.

ERTH scheduler: enhanced red-tailed hawk algorithm for multi-cost optimization in cloud task scheduling

Effective task scheduling has become the key to optimizing resource allocation, reducing operation costs, and enhancing the user experience. The complexity and dynamics of cloud computing environments require task scheduling algorithms that can flexibly respond to multiple computing demands and changing resource states. Therefore, we propose an enhanced Red-tailed Hawk algorithm (named ERTH) based on multiple elite policies and chaotic mapping, while applying this approach in conjunction with the proposed scheduling model to optimize the efficiency of task scheduling in cloud computing environments. We apply the ERTH algorithm to a real cloud computing environment and conduct a comparison with the original RTH and other conventional algorithms. The proposed ERTH algorithm has better convergence speed and stability in most cases of small and large-scale tasks and performs better in minimizing the task completion time and system load cost. Specifically, our experiments show that the ERTH algorithm reduces the total system cost by 34.8% and 36.4% relative to the traditional algorithm for tasks of different sizes. Further, evaluations in the IEEE Congress on Evolutionary Computation (CEC) benchmark test sets show that the ERTH algorithm outperforms the traditional or emerging algorithms in several performance metrics such as mean, standard deviation, etc. The proposal and validation of the ERTH algorithm are of great significance in promoting the application of intelligent optimization algorithms in cloud computing.

Fast Yet Effective Machine Unlearning.

Unlearning the data observed during the training of a machine learning (ML) model is an important task that can play a pivotal role in fortifying the privacy and security of ML-based applications. This article raises the following questions: 1) can we unlearn a single or multiple class(es) of data from an ML model without looking at the full training data even once? and 2) can we make the process of unlearning fast and scalable to large datasets, and generalize it to different deep networks? We introduce a novel machine unlearning framework with error-maximizing noise generation and impair-repair based weight manipulation that offers an efficient solution to the above questions. An error-maximizing noise matrix is learned for the class to be unlearned using the original model. The noise matrix is used to manipulate the model weights to unlearn the targeted class of data. We introduce impair and repair steps for a controlled manipulation of the network weights. In the impair step, the noise matrix along with a very high learning rate is used to induce sharp unlearning in the model. Thereafter, the repair step is used to regain the overall performance. With very few update steps, we show excellent unlearning while substantially retaining the overall model accuracy. Unlearning multiple classes requires a similar number of update steps as for a single class, making our approach scalable to large problems. Our method is quite efficient in comparison to the existing methods, works for multiclass unlearning, does not put any constraints on the original optimization mechanism or network design, and works well in both small and large-scale vision tasks. This work is an important step toward fast and easy implementation of unlearning in deep networks. Source code: https://github.com/vikram2000b/Fast-Machine-Unlearning.

Job training and search assistance for microwork: Evidence from Haiti

This paper presents the findings of a randomized experiment in Haiti aimed at improving online labor market outcomes through training individuals in microworking, a type of work involving small digital tasks completed via online platforms. Six months post-program, we observe significant positive impacts on platform-related microwork outcomes and some broader labor market outcomes. The treatment increases the likelihood of having a microwork profile, the number of tasks completed, hours worked, and microwork earnings, leading to a larger percentage of monthly income from microwork. The program also enhances socioemotional skills and English ability. However, we observe no significant effects on current employment and related outcomes, possibly as participants view microwork as a supplementary activity rather than employment.

Accurate UAV Small Object Detection Based on HRFPN and EfficentVMamba.

(1) Background: Small objects in Unmanned Aerial Vehicle (UAV) images are often scattered throughout various regions of the image, such as the corners, and may be blocked by larger objects, as well as susceptible to image noise. Moreover, due to their small size, these objects occupy a limited area in the image, resulting in a scarcity of effective features for detection. (2) Methods: To address the detection of small objects in UAV imagery, we introduce a novel algorithm called High-Resolution Feature Pyramid Network Mamba-Based YOLO (HRMamba-YOLO). This algorithm leverages the strengths of a High-Resolution Network (HRNet), EfficientVMamba, and YOLOv8, integrating a Double Spatial Pyramid Pooling (Double SPP) module, an Efficient Mamba Module (EMM), and a Fusion Mamba Module (FMM) to enhance feature extraction and capture contextual information. Additionally, a new Multi-Scale Feature Fusion Network, High-Resolution Feature Pyramid Network (HRFPN), and FMM improved feature interactions and enhanced the performance of small object detection. (3) Results: For the VisDroneDET dataset, the proposed algorithm achieved a 4.4% higher Mean Average Precision (mAP) compared to YOLOv8-m. The experimental results showed that HRMamba achieved a mAP of 37.1%, surpassing YOLOv8-m by 3.8% (Dota1.5 dataset). For the UCAS_AOD dataset and the DIOR dataset, our model had a mAP 1.5% and 0.3% higher than the YOLOv8-m model, respectively. To be fair, all the models were trained without a pre-trained model. (4) Conclusions: This study not only highlights the exceptional performance and efficiency of HRMamba-YOLO in small object detection tasks but also provides innovative solutions and valuable insights for future research.

EL-YOLO: An efficient and lightweight low-altitude aerial objects detector for onboard applications

Existing deep learning-based low-altitude small object detectors are typically complex in model architecture and demand substantial computational resources, making deployment for real-time detection tasks on edge computing devices challenging. To address this issue, we proposed EL-YOLO, an efficient and lightweight onboard applications object detector. Initially, in order to maintain a lightweight design and improve model accuracy, we propose a novel approach called Sparsely Connected Asymptotic Feature Pyramid Network(SCAFPN). This approach aims to eliminate inter-layer interference during feature fusion, thereby enhancing the model’s performance. Furthermore, to establish long-range contextual relationships for small object scale information, we devise a Cross-Space Learning Multi-Head Self-Attention mechanism (CSL-MHSA). To assess EL-YOLO capability for onboard small object detection, we deploy it on the embedded NVIDIA Jetson Xavier Nx platform and employ NVIDIA TensorRT FP16 quantization acceleration. On the VisDrone2019-DET and AI-TOD datasets, EL-YOLO demonstrates a 12.4% and 1.3% improvement in mAP50 compared to YOLOv5s. In comparison with the state-of-the-art YOLOv8s proposed in 2023, it achieves a respective 2.8% and 10.7% increase in mAP50. Moreover, the inference speed for the Small model reaches 24 frames per second, while the Nano model achieves 35 frames per second. This method holds promise for direct integration onto unmanned aerial vehicles for aerial small object detection tasks in the future.

Dynamic payment on microtasking platforms using bee colony optimization

Microtasking involves breaking down a job into smaller tasks and assigning them to a group of workers who voluntarily complete the tasks and receive payment. However, the joint estimation of quality and determination of payment remains an underexplored area in microtask crowdsourcing research. This paper addresses the limitation of unestimated payment on microtasking platforms by introducing a dynamic worker quality and payment estimation algorithm known as Dynamic Quality Payment (DQP). Utilizing the Bee Colony Optimization (BCO) algorithm, the proposed approach integrates worker quality estimation and payment determination. DQP incorporates the Gaussian Process Model (GPM) to initially estimate worker quality and then optimize payments based on the quality of work. Empirical testing of the algorithm is conducted using two datasets from Amazon Mechanical Turk. Additionally, the DQP algorithm is compared against novel microtasking and quality estimation algorithms, demonstrating superior performance. The experimental results illustrate that DQP not only reduces the cost of microtasking but also accurately estimates worker quality.

Multi-task neural networks by learned contextual inputs

This paper explores learned-context neural networks. It is a multi-task learning architecture based on a fully shared neural network and an augmented input vector containing trainable task parameters. The architecture is interesting due to its powerful task adaption mechanism, which facilitates a low-dimensional task parameter space. Theoretically, we show that a scalar task parameter is sufficient for universal approximation of all tasks, which is not necessarily the case for more common architectures. Empirically it is shown that, for homogeneous tasks, the dimension of the task parameter may vary with the complexity of the tasks, but a small task parameter space is generally viable. The task parameter space is found to be well-behaved, which simplifies workflows related to updating models as new data arrives, and learning new tasks with the shared parameters are frozen. Additionally, the architecture displays robustness towards datasets where tasks have few data points. The architecture’s performance is compared to similar neural network architectures on ten datasets, with competitive results.

Audiovisual Speech Perception Benefits are Stable from Preschool through Adolescence.

The ability to leverage visual cues in speech perception- especially in noisy backgrounds- is well established from infancy to adulthood. Yet, the developmental trajectory of audiovisual benefits stays a topic of debate. The inconsistency in findings can be attributed to relatively small sample sizes or tasks that are not appropriate for given age groups. We designed an audiovisual speech perception task that was cognitively and linguistically age-appropriate from preschool to adolescence and recruited a large sample ( N = 161) of children (age 4-15). We found that even the youngest children show reliable speech perception benefits when provided with visual cues and that these benefits are consistent throughout development when auditory and visual signals match. Individual variability is explained by how the child experiences their speech-in-noise performance rather than the quality of the signal itself. This underscores the importance of visual speech for young children who are regularly in noisy environments like classrooms and playgrounds.

Workplace small talk and task performance: the chain mediation role of relational energy and positive affect

Purpose Small talk, often regarded as a superficial interaction unrelated to work, is a pervasive and inescapable aspect of daily life and professional settings. In China, where the notion of guanxi – the cultivation of strategic relationships – is deeply valued, workplace small talk (WST) is a strategic tool used by employees to strengthen their interpersonal networks. This study aims to investigate the positive impact of WST on task performance within the Chinese workplace and explores the mechanisms underpinning this relationship. Design/methodology/approach This study adopted a time-lagged research design to test its hypotheses using data from 516 employees across various Chinese firms. Findings This study revealed that WST exerts both direct and indirect positive effects on task performance. It boosts task performance indirectly via two mediators: relational energy and positive affect. This study also delineated a chain mediation model wherein WST sequentially elevates task performance by first enhancing relational energy and then fostering positive affect. Originality/value Counter to the prevailing focus on the negative repercussions of WST, this study sheds light on its beneficial outcomes, proposing novel pathways connecting WST to task performance. These insights contribute to both academic discourse and the development of practical management strategies.

An Improved U-Net Infrared Small Target Detection Algorithm Based on Multi-Scale Feature Decomposition and Fusion and Attention Mechanism.

Infrared small target detection technology plays a crucial role in various fields such as military reconnaissance, power patrol, medical diagnosis, and security. The advancement of deep learning has led to the success of convolutional neural networks in target segmentation. However, due to challenges like small target scales, weak signals, and strong background interference in infrared images, convolutional neural networks often face issues like leakage and misdetection in small target segmentation tasks. To address this, an enhanced U-Net method called MST-UNet is proposed, the method combines multi-scale feature decomposition and fusion and attention mechanisms. The method involves using Haar wavelet transform instead of maximum pooling for downsampling in the encoder to minimize feature loss and enhance feature utilization. Additionally, a multi-scale residual unit is introduced to extract contextual information at different scales, improving sensory field and feature expression. The inclusion of a triple attention mechanism in the encoder structure further enhances multidimensional information utilization and feature recovery by the decoder. Experimental analysis on the NUDT-SIRST dataset demonstrates that the proposed method significantly improves target contour accuracy and segmentation precision, achieving IoU and nIoU values of 80.09% and 80.19%, respectively.

Improved YOLOv8 algorithms for small object detection in aerial imagery

In drone aerial target detection tasks, a high proportion of small targets and complex backgrounds often lead to false positives and missed detections, resulting in low detection accuracy. To improve the accuracy of the detection of small targets, this study proposes two improved models based on YOLOv8s, named IMCMD_YOLOv8_small and IMCMD_YOLOv8_large. Each model accommodates different application scenarios. First, the network structure was optimized by removing the backbone P5 layer used to detect large targets and merging the P4, P3, and P2 layers, which are better suited for detecting medium and small targets; P3 and P2 serve as detection heads to focus more on small targets. Subsequently, the coordinate attention mechanism is integrated into the backbone’s C2f, to create a C2f_CA module that enhances the model’ s focus on key information and secures a richer flow of gradient information. Subsequently, a multiscale attention feature fusion module was designed to merge the shallow and deep features. Finally, a Dynamic Head was introduced to unify the perception of scale, space, and tasks, further enhancing the detection capability for small targets. Experimental results on the VisDrone2019 dataset demonstrated that, compared with YOLOv8s, IMCMD_YOLOv8_small achieved improvements of 7.7% and 5.1% in mAP@0.5 and mAP@0.5:0.95, respectively, with a 73.0% reduction in the parameter count. The IMCMD_YOLOv8_large model showed even more significant improvements in these metrics, reaching 10.8% and 7.3%, respectively, with a 47.7% reduction in the parameter count, displaying superior performance in small target detection tasks. The improved models not only enhanced the detection accuracy but also achieved model lightweighting, thereby proving the effectiveness of the improvement strategies and showcasing superior performance compared with other classic models.

Efficient Defect Classification Using Few-Shot Image Generation and Self-Attention Fused Convolution Features

Although deep learning has been proven to significantly outperform most traditional methods in the classification of large-scale balanced image datasets, collecting enough samples for defect classification is extremely time-consuming and costly. In this paper, we propose a lightweight defect classification method based on few-shot image generation and self-attention fused convolution features. We constructed a 4-class dataset using welding seam images collected from a solar cell module packaging production line. To address the issue of limited defect samples, especially for classes with less than 10 images, we implemented two strategies. Geometric enhancement techniques were first used to extend the defective images. Secondly, multi-scale feature fusion Generative Adversarial Networks (GANs) were utilized to further enhance the dataset. We then performed the feature-level fusion of convolution neural networks and self-attention networks, achieving a classification accuracy of 98.19%. Our experimental results demonstrate that the proposed model performs well in small sample defect classification tasks. And, it can be effectively applied to product quality inspection tasks in industrial production lines.

LLMs and Spatial Reasoning: Assessing Roadblocks and Providing Pathways to Improvement

In this paper, we show how relative location prompting can improve how Large Language Models (LLMs) such as ChatGPT interact with Spatial Reasoning (SR) tasks. LLMs likely have difficulty with SR tasks due to being designed for language based tasks, whilst SR tasks are more visual (Lee, 2023). By reading papers on Self-Ask (Press et al., 2023) and Chain-of-thought (Jason Zhanshun Wei et al., 2022) and recognizing their success, we hypothesized that prompting techniques similar to the ones mentioned would be effective in increasing the success-rate of the LLM agent in our Spatial Reasoning task. Taking these two factors into account, the solution we came up with was to turn the multi-step interaction-based SR tasks into more simple tasks by prompting the AI agent with its relative location to the target location after each step taken. We set up a 2D 5x5 grid world environment to test the LLM agent against, and by setting up a separate environment which includes relative location prompting, as well as a random environment, we saw the difference between the three success-rates. We collected and analysed data of 300 trials total (100 trials on each of the 3 environments) to conclude that relative location prompting does improve the success rate of LLMs when tackling SR tasks. This showed that by converting SR tasks into text, and by breaking down large tasks into smaller tasks, AI can solve SR problems better. Future studies should investigate other types of SR tasks, such as folding scenarios, and test out different prompting methods to determine the best one.

Research on Task Scheduling for Internet of Things Cloud Computing Based on Improved Chicken Swarm Optimization Algorithm

Aiming at the shortcomings of long completion time and high consumption cost of cloud computing batch task scheduling in IoT, an Improved Chicken Swarm Optimization Algorithm (ICSO) for task scheduling in cloud computing scenarios is proposed. Specifically, in order to solve the problems of slow convergence and falling into local optimum of the chicken swarm optimization algorithm, we adopt the nonlinear decreasing technique of the rooster and the weighting technique of the hen, optimize the following coefficients of the chicks, and apply ICSO to cloud computing task scheduling. In simulation experiments, we conducted a large number of experiments using four standard benchmark functions with different number of tasks and the results show that ICSO algorithm reduces 25.8%, 9.3%, 8.8%, 7.5% in small task time compared to CSO, DCSO, GCSO, ABCSO in large task time by 30.8%, 8.3%, 7.8%, 6.3%, 11.8%, 10.3%, 8.8%, 7.5% savings in small task cost and 25.8%, 11.2%, 10.8%, 9.3% savings in large task cost. This method effectively reduces task scheduling time and cost consumption. Meanwhile, we tested it in combination with an IoT-based cloud platform and achieved very satisfying Results.

Crater Triangle Matching Algorithm Based on Fused Geometric and Regional Features

Craters are regarded as significant navigation landmarks during the descent and landing process in small body exploration missions for their universality. Recognizing and matching craters is a crucial prerequisite for visual and LIDAR-based navigation tasks. Compared to traditional algorithms, deep learning-based crater detection algorithms can achieve a higher recognition rate. However, matching crater detection results under various image transformations still poses challenges. To address the problem, a composite feature-matching algorithm that combines geometric descriptors and region descriptors (extracting normalized region pixel gradient features as feature vectors) is proposed. First, the geometric configuration map is constructed based on the crater detection results. Then, geometric descriptors and region descriptors are established within each feature primitive of the map. Subsequently, taking the salience of geometric features into consideration, composite feature descriptors with scale, rotation, and illumination invariance are generated through fusion geometric and region descriptors. Finally, descriptor matching is accomplished by computing the relative distances between descriptors and adhering to the nearest neighbor principle. Experimental results show that the composite feature descriptor proposed in this paper has better matching performance than only using shape descriptors or region descriptors, and can achieve a more than 90% correct matching rate, which can provide technical support for the small body visual navigation task.

FocusDet: an efficient object detector for small object

The object scale of a small object scene changes greatly, and the object is easily disturbed by a complex background. Generic object detectors do not perform well on small object detection tasks. In this paper, we focus on small object detection based on FocusDet. FocusDet refers to the small object detector proposed in this paper. It consists of three parts: backbone, feature fusion structure, and detection head. STCF-EANet was used as the backbone for feature extraction, the Bottom Focus-PAN for feature fusion, and the detection head for object localization and recognition.To maintain sufficient global context information and extract multi-scale features, the STCF-EANet network backbone is used as the feature extraction network.PAN is a feature fusion module used in general object detectors. It is used to perform feature fusion on the extracted feature maps to supplement feature information.In the feature fusion network, FocusDet uses Bottom Focus-PAN to capture a wider range of locations and lower-level feature information of small objects.SIOU-SoftNMS is the proposed algorithm for removing redundant prediction boxes in the post-processing stage. SIOU multi-dimension accurately locates the prediction box, and SoftNMS uses the Gaussian algorithm to remove redundant prediction boxes. FocusDet uses SIOU-SoftNMS to address the missed detection problem common in dense tiny objects.The VisDrone2021-DET and CCTSDB2021 object detection datasets are used as benchmarks, and tests are carried out on VisDrone2021-det-test-dev and CCTSDB-val datasets. Experimental results show that FocusDet improves mAP@.5% from 33.6% to 46.7% on the VisDrone dataset. mAP@.5% on the CCTSDB2021 dataset is improved from 81.6% to 87.8%. It is shown that the model has good performance for small object detection, and the research is innovative.

SPContrastNet: A Self-Paced Contrastive Learning Model for Few-Shot Text Classification

Meta-learning has recently promoted few-shot text classification, which identifies target classes based on information transferred from source classes through a series of small tasks or episodes. Existing works constructing their meta-learner on Prototypical Networks need improvement in learning discriminative text representations between similar classes that may lead to conflicts in label prediction. The overfitting problems caused by a few training instances need to be adequately addressed. In addition, efficient episode sampling procedures that could enhance few-shot training should be utilized. To address the problems mentioned above, we first present a contrastive learning framework that simultaneously learns discriminative text representations via supervised contrastive learning while mitigating the overfitting problem via unsupervised contrastive regularization, and then we build an efficient self-paced episode sampling approach on top of it to include more difficult episodes as training progresses. Empirical results on eight few-shot text classification datasets show that our model outperforms the current state-of-the-art models. The extensive experimental analysis demonstrates that our supervised contrastive representation learning and unsupervised contrastive regularization techniques improve the performance of few-shot text classification. The episode-sampling analysis reveals that our self-paced sampling strategy improves training efficiency.

Can LLM Replace Stack Overflow? A Study on Robustness and Reliability of Large Language Model Code Generation

Recently, large language models (LLMs) have shown an extraordinary ability to understand natural language and generate programming code. It has been a common practice for software engineers to consult LLMs when encountering coding questions. Although efforts have been made to avoid syntax errors and align the code with the intended semantics, the reliability, and robustness of the code generation from LLMs have not yet been thoroughly studied. The executable code is not equivalent to reliable and robust code, especially in the context of real-world software development. For example, the misuse of APIs in the generated code could lead to severe problems, such as resource leaks, program crashes, etc. Existing code evaluation benchmarks and datasets focus on crafting small tasks such as programming questions in coding interviews, which, however, deviates from the problem that developers would ask LLM for real-world coding help. To fill the missing piece, in this work, we propose a dataset RobustAPI for evaluating the reliability and robustness of code generated by LLMs. We collect 1208 coding questions from Stack Overflow on 18 representative Java APIs. We summarize the common misuse patterns of these APIs and evaluate them on current popular LLMs. The evaluation results show that even for GPT-4, 62% of the generated code contains API misuses, which would cause unexpected consequences if the code is introduced into real-world software.