Augmentation Strategies Research Articles

No More Shortcuts: Realizing the Potential of Temporal Self-Supervision

Self-supervised approaches for video have shown impressive results in video understanding tasks. However, unlike early works that leverage temporal self-supervision, current state-of-the-art methods primarily rely on tasks from the image domain (e.g., contrastive learning) that do not explicitly promote the learning of temporal features. We identify two factors that limit existing temporal self-supervision: 1) tasks are too simple, resulting in saturated training performance, and 2) we uncover shortcuts based on local appearance statistics that hinder the learning of high-level features. To address these issues, we propose 1) a more challenging reformulation of temporal self-supervision as frame-level (rather than clip-level) recognition tasks and 2) an effective augmentation strategy to mitigate shortcuts. Our model extends a representation of single video frames, pre-trained through contrastive learning, with a transformer that we train through temporal self-supervision. We demonstrate experimentally that our more challenging frame-level task formulations and the removal of shortcuts drastically improve the quality of features learned through temporal self-supervision. Our extensive experiments show state-of-the-art performance across 10 video understanding datasets, illustrating the generalization ability and robustness of our learned video representations. Project Page: https://daveishan.github.io/nms-webpage.

Semi-supervised 3D Object Detection with PatchTeacher and PillarMix

Semi-supervised learning aims to leverage numerous unlabeled data to improve the model performance. Current semi-supervised 3D object detection methods typically use a teacher to generate pseudo labels for a student, and the quality of the pseudo labels is essential for the final performance. In this paper, we propose PatchTeacher, which focuses on partial scene 3D object detection to provide high-quality pseudo labels for the student. Specifically, we divide a complete scene into a series of patches and feed them to our PatchTeacher sequentially. PatchTeacher leverages the low memory consumption advantage of partial scene detection to process point clouds with a high-resolution voxelization, which can minimize the information loss of quantization and extract more fine-grained features. However, it is non-trivial to train a detector on fractions of the scene. Therefore, we introduce three key techniques, i.e., Patch Normalizer, Quadrant Align, and Fovea Selection, to improve the performance of PatchTeacher. Moreover, we devise PillarMix, a strong data augmentation strategy that mixes truncated pillars from different LiDAR scans to generate diverse training samples and thus help the model learn more general representation. Extensive experiments conducted on Waymo and ONCE datasets verify the effectiveness and superiority of our method and we achieve new state-of-the-art results, surpassing existing methods by a large margin. Codes are available at https://github.com/LittlePey/PTPM.

Toward Robustness in Multi-Label Classification: A Data Augmentation Strategy against Imbalance and Noise

Multi-label classification poses challenges due to imbalanced and noisy labels in training data. In this paper, we propose a unified data augmentation method, named BalanceMix, to address these challenges. Our approach includes two samplers for imbalanced labels, generating minority-augmented instances with high diversity. It also refines multi-labels at the label-wise granularity, categorizing noisy labels as clean, re-labeled, or ambiguous for robust optimization. Extensive experiments on three benchmark datasets demonstrate that BalanceMix outperforms existing state-of-the-art methods. We release the code at https://github.com/DISL-Lab/BalanceMix.

NegVSR: Augmenting Negatives for Generalized Noise Modeling in Real-world Video Super-Resolution

The capability of video super-resolution (VSR) to synthesize high-resolution (HR) video from ideal datasets has been demonstrated in many works. However, applying the VSR model to real-world video with unknown and complex degradation remains a challenging task. First, existing degradation metrics in most VSR methods are not able to effectively simulate real-world noise and blur. On the contrary, simple combinations of classical degradation are used for real-world noise modeling, which led to the VSR model often being violated by out-of-distribution noise. Second, many SR models focus on noise simulation and transfer. Nevertheless, the sampled noise is monotonous and limited. To address the aforementioned problems, we propose a Negatives augmentation strategy for generalized noise modeling in Video Super-Resolution (NegVSR) task. Specifically, we first propose sequential noise generation toward real-world data to extract practical noise sequences. Then, the degeneration domain is widely expanded by negative augmentation to build up various yet challenging real-world noise sets. We further propose the augmented negative guidance loss to learn robust features among augmented negatives effectively. Extensive experiments on real-world datasets (e.g., VideoLQ and FLIR) show that our method outperforms state-of-the-art methods with clear margins, especially in visual quality. Project page is available at: https://negvsr.github.io/.

DiffusionEdge: Diffusion Probabilistic Model for Crisp Edge Detection

Limited by the encoder-decoder architecture, learning-based edge detectors usually have difficulty predicting edge maps that satisfy both correctness and crispness. With the recent success of the diffusion probabilistic model (DPM), we found it is especially suitable for accurate and crisp edge detection since the denoising process is directly applied to the original image size. Therefore, we propose the first diffusion model for the task of general edge detection, which we call DiffusionEdge. To avoid expensive computational resources while retaining the final performance, we apply DPM in the latent space and enable the classic cross-entropy loss which is uncertainty-aware in pixel level to directly optimize the parameters in latent space in a distillation manner. We also adopt a decoupled architecture to speed up the denoising process and propose a corresponding adaptive Fourier filter to adjust the latent features of specific frequencies. With all the technical designs, DiffusionEdge can be stably trained with limited resources, predicting crisp and accurate edge maps with much fewer augmentation strategies. Extensive experiments on four edge detection benchmarks demonstrate the superiority of DiffusionEdge both in correctness and crispness. On the NYUDv2 dataset, compared to the second best, we increase the ODS, OIS (without post-processing) and AC by 30.2%, 28.1% and 65.1%, respectively. Code: https://github.com/GuHuangAI/DiffusionEdge.

ISP-Teacher:Image Signal Process with Disentanglement Regularization for Unsupervised Domain Adaptive Dark Object Detection

Object detection in dark conditions has always been a great challenge due to the complex formation process of low-light images. Currently, the mainstream methods usually adopt domain adaptation with Teacher-Student architecture to solve the dark object detection problem, and they imitate the dark conditions by using non-learnable data augmentation strategies on the annotated source daytime images. Note that these methods neglected to model the intrinsic imaging process, i.e. image signal processing (ISP), which is important for camera sensors to generate low-light images. To solve the above problems, in this paper, we propose a novel method named ISP-Teacher for dark object detection by exploring Teacher-Student architecture from a new perspective (i.e. self-supervised learning based ISP degradation). Specifically, we first design a day-to-night transformation module that consistent with the ISP pipeline of the camera sensors (ISP-DTM) to make the augmented images look more in line with the natural low-light images captured by cameras, and the ISP-related parameters are learned in a self-supervised manner. Moreover, to avoid the conflict between the ISP degradation and detection tasks in a shared encoder, we propose a disentanglement regularization (DR) that minimizes the absolute value of cosine similarity to disentangle two tasks and push two gradients vectors as orthogonal as possible. Extensive experiments conducted on two benchmarks show the effectiveness of our method in dark object detection. In particular, ISP-Teacher achieves an improvement of +2.4% AP and +3.3% AP over the SOTA method on BDD100k and SHIFT datasets, respectively. The code can be found at https://github.com/zhangyin1996/ISP-Teacher.

Self-Supervised Representation Learning with Meta Comprehensive Regularization

Self-Supervised Learning (SSL) methods harness the concept of semantic invariance by utilizing data augmentation strategies to produce similar representations for different deformations of the same input. Essentially, the model captures the shared information among multiple augmented views of samples, while disregarding the non-shared information that may be beneficial for downstream tasks. To address this issue, we introduce a module called CompMod with Meta Comprehensive Regularization (MCR), embedded into existing self-supervised frameworks, to make the learned representations more comprehensive. Specifically, we update our proposed model through a bi-level optimization mechanism, enabling it to capture comprehensive features. Additionally, guided by the constrained extraction of features using maximum entropy coding, the self-supervised learning model learns more comprehensive features on top of learning consistent features. In addition, we provide theoretical support for our proposed method from information theory and causal counterfactual perspective. Experimental results show that our method achieves significant improvement in classification, object detection and semantic segmentation tasks on multiple benchmark datasets.

Semi-supervised Class-Agnostic Motion Prediction with Pseudo Label Regeneration and BEVMix

Class-agnostic motion prediction methods aim to comprehend motion within open-world scenarios, holding significance for autonomous driving systems. However, training a high-performance model in a fully-supervised manner always requires substantial amounts of manually annotated data, which can be both expensive and time-consuming to obtain. To address this challenge, our study explores the potential of semi-supervised learning (SSL) for class-agnostic motion prediction. Our SSL framework adopts a consistency-based self-training paradigm, enabling the model to learn from unlabeled data by generating pseudo labels through test-time inference. To improve the quality of pseudo labels, we propose a novel motion selection and re-generation module. This module effectively selects reliable pseudo labels and re-generates unreliable ones. Furthermore, we propose two data augmentation strategies: temporal sampling and BEVMix. These strategies facilitate consistency regularization in SSL. Experiments conducted on nuScenes demonstrate that our SSL method can surpass the self-supervised approach by a large margin by utilizing only a tiny fraction of labeled data. Furthermore, our method exhibits comparable performance to weakly and some fully supervised methods. These results highlight the ability of our method to strike a favorable balance between annotation costs and performance. Code will be available at https://github.com/kwwcv/SSMP.

I Prefer Not to Say: Protecting User Consent in Models with Optional Personal Data

We examine machine learning models in a setup where individuals have the choice to share optional personal information with a decision-making system, as seen in modern insurance pricing models. Some users consent to their data being used whereas others object and keep their data undisclosed. In this work, we show that the decision not to share data can be considered as information in itself that should be protected to respect users' privacy. This observation raises the overlooked problem of how to ensure that users who protect their personal data do not suffer any disadvantages as a result. To address this problem, we formalize protection requirements for models which only use the information for which active user consent was obtained. This excludes implicit information contained in the decision to share data or not. We offer the first solution to this problem by proposing the notion of Protected User Consent (PUC), which we prove to be loss-optimal under our protection requirement. We observe that privacy and performance are not fundamentally at odds with each other and that it is possible for a decision maker to benefit from additional data while respecting users' consent. To learn PUC-compliant models, we devise a model-agnostic data augmentation strategy with finite sample convergence guarantees. Finally, we analyze the implications of PUC on challenging real datasets, tasks, and models.

Are You Concerned about Limited Function Evaluations: Data-Augmented Pareto Set Learning for Expensive Multi-Objective Optimization

Optimizing multiple conflicting black-box objectives simultaneously is a prevalent occurrence in many real-world applications, such as neural architecture search, and machine learning. These problems are known as expensive multi-objective optimization problems (EMOPs) when the function evaluations are computationally or financially costly. Multi-objective Bayesian optimization (MOBO) offers an efficient approach to discovering a set of Pareto optimal solutions. However, the data deficiency issue caused by limited function evaluations has posed a great challenge to current optimization methods. Moreover, most current methods tend to prioritize the quality of candidate solutions, while ignoring the quantity of promising samples. In order to tackle these issues, our paper proposes a novel multi-objective Bayesian optimization algorithm with a data augmentation strategy that provides ample high-quality samples for Pareto set learning (PSL). Specifically, it utilizes Generative Adversarial Networks (GANs) to enrich data and a dominance prediction model to screen out high-quality samples, mitigating the predicament of limited function evaluations in EMOPs. Additionally, we adopt the regularity model to expensive multi-objective Bayesian optimization for PSL. Experimental results on both synthetic and real-world problems demonstrate that our algorithm outperforms several state-of-the-art and classical algorithms.

Abstract 2304: Detection of early-disseminated cancer cells with deep learning-enabled holographic imaging

Abstract Recent research increasingly validates the early dissemination of tumor cells in peripheral blood during the nascent stages of cancer, often preceding clinical identification of the primary tumor. This emerging evidence emphasizes the potential of Circulating Tumor Cells (CTCs) as early indicators for cancer. Despite their significance, CTCs are exceptionally rare compared to normal blood cells, which presents a considerable challenge in detection, particularly during early stages of cancer. Traditional detection methods, such as those based on nucleated cell enrichment, antibody labeling and fluorescence imaging, encounter notable limitations when applied in the context of early detection. These limitations arise from the inherent heterogeneity of CTCs, and the multistep process involved in labeling and manual enumeration, compromising cell viability and resulting in cell loss. This loss becomes particularly problematic in the context of early cancer detection scenarios where the tumor burden is extremely low, and any cell loss can significantly impact assay sensitivity. To overcome these challenges, we propose an innovative CTC detection approach employing a deep learning framework combined with holographic imaging. This technique utilizes coherent light to generate holograms from cell samples, capturing detailed 3D morphological and optical properties of individual cells. We developed a custom convolutional neural network designed to facilitate high-throughput cell sorting in real-time. Trained on healthy blood samples and diverse cancer cell lines, the dataset consists of more than 50 million cellular holograms enhanced by proprietary Gaussian annotation and image augmentation strategies. Moreover, by combining the morphological signatures from holography with antigen signatures (e.g. HER2/ER/PR) in real-time, our model demonstrates the ability to detect less than 1 false positive per 1 million nucleated cells, highlighting its potential as a robust tool for targeted early-stage breast cancer detection. Our technology represents highly sensitive alternative to traditional screening methods, with the promise of enhancing patient outcomes. Citation Format: Nicholas Heller, Kevin Mallery, Nathaniel Bristow, Yash Travadi, Eng Hock Lee, Jiarong Hong. Detection of early-disseminated cancer cells with deep learning-enabled holographic imaging [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 2304.

An RGB‐D object detection model with high‐generalization ability applied to tea harvesting robot for outdoor cross‐variety tea shoots detection

AbstractDetecting tea shoots is the first and most crucial step in achieving intelligent tea harvesting. However, when faced with thousands of tea varieties, establishing a high‐quality and comprehensive database comes with significant costs. Therefore, it has become an urgent challenge to improve the model's generalization ability and train it with minimal samples to develop a model capable of achieving optimal detection performance in various environments and tea varieties. This paper introduces a model named You Only See Tea (YOST) which utilizes depth maps to enhance model's generalization ability. It is applied to detect tea shoots in complex environments and to perform cross‐variety tea shoots detection. Our approach differs from common data augmentation strategies aimed at enhancing model generalization by diversifying the data set. Instead, we enhance the model's learning capability by strategically amplifying its attention towards core target features while simultaneously reducing attention towards noncore features. The proposed module YOST is developed upon the You Only Look Once version 7 (YOLOv7) model, utilizing two shared‐weight backbone networks to process both RGB and depth images. Then further integrate two modalities with feature layers at the same scale into our designed Ultra‐attention Fusion and Activation Module. By utilizing this approach, the model can proficiently detect targets by capturing core features, even when encountering complex environments or unfamiliar tea leaf varieties. The experimental results indicate that YOST displayed faster and more consistent convergence compared with YOLOv7 in training. Additionally, YOST demonstrated a 6.58% enhancement in AP50 for detecting tea shoots in complex environments. Moreover, when faced with a cross‐variety tea shoots detection task involving multiple unfamiliar varieties, YOST showcased impressive generalization abilities, achieving a significant maximum AP50 improvement of 33.31% compared with YOLOv7. These findings establish its superior performance. Our research departs from the heavy reliance on high‐generalization models on a large number of training samples, making it easier to train small‐scale, high‐generalization models. This approach significantly alleviates the pressure associated with data collection and model training.

Online Defect Detection in LGA Crystallization Imaging Using MANet-Based Deep Learning Image Analysis

In this paper, a MANet-based image detection approach is designed to inspect crystal defects during the cooling crystallization process, like that involving β-form L-glutamic acid (LGA), utilizing an online imaging device. The steps in the presented strategy encompass crystal image preprocessing, crystal image segmentation, and crystal classification. Firstly, the guided image filter is introduced to preprocess the collected crystallization images for offline training and online detection. Then, by using an image augmentation strategy to enlarge the number of crystal image samples for training, the MANet-based network is improved for crystal image segmentation. Accordingly, by defining some features, needle-like crystals can be categorized into four types with an efficient classifier for the detection of normal and defective crystals. The experimental results for the batch crystallization of β-form LGA are provided to illustrate the validity of the presented detection methodology.

AI-supported estimation of safety critical wind shear-induced aircraft go-around events utilizing pilot reports

The occurrence of wind shear and severe thunderstorms during the final approach phase contributes to nearly half of all aviation accidents. Pilots usually employ the go-around procedure in order to lower the likelihood of an unsafe landing. However, multiple factors influence the go-arounds induced by wind shear. In order to predict the wind shear-induced go-around, this study utilized a cutting-edge AI-based Combined Kernel and Tree Boosting (KTBoost) framework with various data augmentation strategies. First, the KTBoost model was trained, tested, and compared to other Machine Learning models using the data extracted from Hong Kong International Airport (HKIA)-based Pilot Reports for the years 2017–2021. The performance evaluation revealed that the KTBoost model with Synthetic Minority Oversampling Technique - Edited Nearest Neighbor (SMOTE-ENN)- augmented data demonstrated superior performance as measured by the F1-Score (94.37%) and G-Mean (94.87%). Subsequently, the SHapley Additive exPlanations (SHAP) approach was employed to elucidate the interpretation of the KTBoost model using data that had been treated with the SMOTE-ENN technique. According to the findings, flight type, wind shear magnitude, and approach runway contributed the most to the wind shear-induced go-around. Compared to international flights, Hong Kong-based airlines endured the highest number of wind shear-induced go-arounds. Shear due to the tailwind contributed more to the go-around than the headwinds. The runways with the most wind shear-induced Go-arounds were 07C and 07R.

Harnessing the power of radiomics and deep learning for improved breast cancer diagnosis with multiparametric breast mammography

Breast cancer, with its high mortality, faces diagnostic challenges due to variability in mammography quality and breast densities, leading to inconsistencies in radiological interpretations. Computer-aided diagnostic (CAD) systems, while helpful, struggle with accurately interpreting lesion characteristics such as morphology, density, and size. To address this, our study developed advanced deep-learning algorithms to improve the detection, localization, risk assessment, and classification of breast lesions, aiming to reduce false positives on human intervention and tackle slow convergence rates. Key innovations of the approach include preprocessing techniques, advanced filtering, and data augmentation strategies to optimize model performance, mitigating over- and under-fitting concerns. A significant development is the Chaotic Leader Selective Filler Swarm Optimization (cLSFSO) method, which effectively detects breast-dense lesions by extracting textural and statistical features. Additionally, the study adapted deep learning models like modified VGGNet and SE-ResNet152 through transfer learning, significantly enhancing their capability to distinguish between normal and suspicious mammography regions. The study also introduces hybrid deep neural network-based approaches, including CNN+LSTM and CNN+SVM, for diagnosing and grading cancerous polyps from the pre-segmented ROIs. Besides, the transfer learning paradigm is employed to boost the efficacy in classifying breast masses and reducing computing time by modifying the final layer of the proposed pre-trained models. The integration of Grad-CAM techniques further refines our analysis, leading to more accurate assessments and improved diagnosis of breast anomalies. Evaluated using benchmark and private datasets, our algorithms demonstrated a sensitivity of 0.99 and an overall AUC of 0.99, indicating significant improvements in mammogram analysis. These advancements aid radiologists, potentially improving patient outcomes and contributing to medical imaging and AI in healthcare.

Diffusion-based Wasserstein generative adversarial network for blood cell image augmentation

White blood cells (WBC) are vital elements of the immune system, and their number and differential count are crucial for diagnosing blood-related disorders. While existing research has primarily focused on classifying easily distinguishable major WBC types, our study delves into a model encompassing up to 19 WBC classes, some of which exhibit irregular shapes and are challenging to differentiate manually. Convolutional Neural Networks (CNNs) have shown remarkable progress in accurately classifying these intricate WBC classes. However, the accuracy of these models depends mainly on the availability of enough appropriate datasets, which can be challenging to obtain for rare WBC classes. To address this, we introduce a generative model, the diffusion-based Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP). This model innovatively combines the Denoising Diffusion Probabilistic Model (DDPM) forward diffusion process with the WGAN-GP, leveraging DDPM’s noisy vectors as inputs for WGAN-GP’s generator. This fusion accelerates the generative process and significantly enhances the output’s fidelity, particularly for complex WBC images. Our model demonstrated its effectiveness on a dataset comprising 4,503 images across 19 WBC classes from Soonchunhyang University Bucheon Hospital, Korea, showing significant improvement in generating high-quality images for rare WBC classes and addressing data imbalance. We further combined pre-trained CNNs with Support Vector Machines (SVM) for classification, where our augmentation strategy led to the ResNet50-SVM model achieving an average accuracy of 95% in classifying the 19 WBC classes. This study not only addresses the data imbalance but also sets a new benchmark in WBC image analysis, demonstrating our model’s efficacy in generating high-quality data for rare classes.

A polar transformation augmentation approach for enhancing mammary gland segmentation in ultrasound images

Environmental factors can detrimentally affect mammary gland development, leading to negative impacts on milk secretion in mammals. Ultrasonography serves as a non-invasive and non-destructive method for assessing mammary gland characteristics and development. Deep learning approaches enable automated monitoring of mammary gland development, though they typically require large, labeled datasets that may be limited by data collection constraints. This study aimed to develop and evaluate a polar transformation-based augmentation strategy to enhance the performance of deep learning algorithms for mammary gland segmentation in small datasets. We collected 405 ultrasound images of mammary glands (front and rear quarters) from 29 crossbred F1 Holstein x Gyr calves aged 5 to 11 weeks. The parenchyma tissue in these images was manually annotated using the VGG Image Annotator. A leave-one-animal-out cross-validation approach was employed to train the semantic segmentation algorithm. In this approach, all images from one calf were used as a testing set, and images from the remaining 28 calves were used for training in each of the 29 iterations. Our proposed method involved utilizing a polar transform technique for data augmentation in ultrasound images and the PSPNet deep learning algorithm for image segmentation. The average F1-score on the testing set was 54% in week 1, 70% in week 2, and 75% in week 3. Our findings revealed that the algorithm’s performance was suboptimal for images with very small parenchyma (week 1). However, as the mammary gland developed, the identification and segmentation of parenchymal tissue significantly improved. The performance of deep learning algorithms in segmenting small tissues could potentially be enhanced by using larger datasets and higher resolution images. In conclusion, our study demonstrates that polar transformation is an effective strategy for augmenting mammary gland ultrasound images, which in turn improves the performance of deep neural networks in segmenting parenchymal tissue.

Use of activity trackers to improve blood pressure in young people at risk for cardiovascular disease: a pilot randomized controlled trial.

Promoting physical activity among young individuals with cardiovascular disease (CVD) risk factors such as hypertension, diabetes, or chronic kidney disease can lower systolic blood pressure (BP). We sought to determine whether a 6-month intervention using a physical activity tracker was feasible and effective, compared with usual care. Participants were recruited at a single academic medical center. Those aged 8-30years were randomized in a 2:1 ratio to either the intervention (use of a Fitbit physical activity tracker coupled with feedback regarding the participant's step count) or usual care. The primary feasibility outcomes were screening-to-enrollment ratio and 6-month retention rates; the primary clinical outcome was a change in systolic BP from 0-6months. Sixty-three participants were enrolled (57% male; mean age: 18 ± 4years). The screening-to-enrollment ratio was 1.8:1. Six-month retention was 62% in the intervention group and 86% in the control group (p = 0.08). Mean change in systolic BP in the intervention group was not significantly different from the control group at 6months (- 2.3mmHg; 95% CI - 6.5, 1.8 vs. 3.0mmHg; 95% CI - 2.5, 8.4, respectively, p = 0.12). Among children and young adults at elevated CVD risk, the use of a physical activity tracker coupled with tailored feedback regarding their step count progress was feasible but not sustained over time. Physical activity tracker use did not have a statistically significant effect on BP after 6months. Augmented strategies to mitigate risk in young patients at high risk for early-onset CVD should be explored. This trial is registered at ClinicalTrials.gov (NCT03325426).

Face Mask Recognition based on YOLOV3

Wearing masks is considered one of the effective ways to prevent epidemics and protect physical health. In densely populated public places, detecting whether the mask is correctly worn has important application value, which can help managers reduce the potential risk of disease transmission. Previous works mainly rely on manual features, which are limited to fully expressing complex scene information. Thanks to the rapid development of artificial intelligence technology, automatic mask detection methods based on deep learning have achieved breakthroughs in speed and accuracy, while mask detection in complex scenes is still an open issue. To alleviate this issue, this paper proposes a mask detection method based on YOLOV3. Specifically, this study introduces regularization methods such as Drop Block and Label Smoothing, as well as data augmentation strategies such as Gridmask and Mosaic. This study further explores the recognition performance for refined scenarios including no mask, standard mask-wearing and incorrect mask-wearing. Extensive experimental results show the effectiveness of our method. By introducing the improved YOLOV5 algorithm to realize the mask detection function, the data structure is optimized through pruning, the data volume is reduced, the calculation speed is accelerated, and the mask detection is well realized.

End Face Detection of Rebar Based on Improved PP YOLO

This paper introduces an improved PP-YOLO network method to enhance the accuracy of rebar end identification and counting in construction engineering. The network is optimized for the specific characteristics of rebar images, enhancing its recognition capabilities for rebars of various sizes and shapes. Notably, the network structure introduces new pathways in the 4th and 5th layers, enabling more effective learning and identification of rebar features from low-level characteristics, thus improving overall recognition and counting accuracy. Additionally, an optimized data augmentation strategy, tailored to the unique features of rebar images, replaces the traditional Mixup method. Specific algorithms are introduced to enhance the network's efficiency in learning rebar image characteristics. These improvements led to excellent performance in rebar end face recognition tests, achieving an average precision (AP) of 96.23%, a 1.07% increase compared to the original model. This significant performance improvement confirms the effectiveness of our proposed improvements in practical applications, offering new perspectives for the development of rebar detection technology in the construction industry.