AI is used in image classification to automatically categorize and label images based on their content. Through deep learning algorithms, neural networks can learn to recognize patterns, objects, and features in images, enabling applications such as facial recognition, object detection, and automated image tagging.
Researchers harness convolutional neural networks (CNNs) to recognize Shen embroidery, achieving 98.45% accuracy. By employing transfer learning and enhancing MobileNet V1 with spatial pyramid pooling, they provide crucial technical support for safeguarding this cultural art form.
Researchers introduced a multi-stage progressive detection method utilizing a Swin transformer to accurately identify water deficit in vertical greenery plants. By integrating classification, semantic segmentation, and object detection, the approach significantly improved detection accuracy compared to traditional methods like R-CNN and YOLO, offering promising solutions for urban greenery management.
Researchers introduced a deep convolutional neural network (DCNN) model for accurately detecting and classifying grape leaf diseases. Leveraging a dataset of grape leaf images, the DCNN model outperformed conventional CNN models, demonstrating superior accuracy and reliability in identifying black rot, ESCA, leaf blight, and healthy specimens.
Researchers integrated gradient quantization (GQ) into DenseNet architecture to improve image recognition (IR). By optimizing feature reuse and introducing GQ for parallel training, they achieved superior accuracy and accelerated training speed, overcoming communication bottlenecks.
This study in Nature explores the application of convolutional neural networks (CNNs) in classifying infrared (IR) images for concealed object detection in security scanning. Leveraging a ResNet-50 model and transfer learning, the researchers refined pre-processing techniques such as k-means and fuzzy-c clustering to improve classification accuracy.
Researchers introduced OCTDL, an open-access dataset comprising over 2000 labeled OCT images of retinal diseases, including AMD, DME, and others. Utilizing high-resolution OCT scans obtained from an Optovue Avanti RTVue XR system, the dataset facilitated the development of deep learning models for disease classification. Validation with VGG16 and ResNet50 architectures demonstrated high performance, indicating OCTDL's potential for advancing automatic processing and early disease detection in ophthalmology.
Recent research in few-shot fine-grained image classification (FSFGIC) has seen the development of various methods, including class representation learning and global/local deep feature representation techniques. These advancements aim to improve generalization, overcome distribution biases, and enhance discriminative feature representation, yet challenges such as overfitting and efficiency persist, necessitating further investigation.
This paper presents the groundbreaking lifelong learning optical neural network (L2ONN), offering efficient and scalable AI systems through photonic computing. L2ONN's innovative architecture harnesses sparse photonic connections and parallel processing, surpassing traditional electronic models in efficiency, capacity, and lifelong learning capabilities, with implications for various applications from vision classification to medical diagnosis.
Researchers explore the use of SqueezeNet, a lightweight convolutional neural network, for tourism image classification, highlighting its evolution from traditional CNNs and its efficiency in processing high-resolution images. Through meticulous experimentation and model enhancements, they demonstrate SqueezeNet's superior performance in accuracy and model size compared to other models like AlexNet and VGG19, advocating for its potential application in enhancing tourism image analysis and promoting tourism destinations.
Chinese researchers introduce a novel approach, inspired by random forest, for constructing deep neural networks using fragmented images and ensemble learning. Demonstrating enhanced accuracy and stability on image classification datasets, the method offers a practical and efficient solution, reducing technical complexity and hardware requirements in deep learning applications.
Researchers introduce MFWD, a meticulously curated dataset capturing the growth of 28 weed species in maize and sorghum fields. This dataset, essential for computer vision in weed management, features high-resolution images, semantic and instance segmentation masks, and demonstrates promising results in multi-species classification, showcasing its potential for advancing automated weed detection and sustainable agriculture practices.
Researchers unveil a regressive vision transformer (RVT) model to tackle the leading cause of death in dogs—cardiac disease. By integrating traditional diagnostic methods with advanced deep learning, the RVT model proves to be efficient, trustworthy, and superior, paving the way for enhanced canine cardiomegaly assessment and revolutionizing diagnostic accuracy in veterinary medicine.
Canadian researchers at Western University and the Vector Institute unveil a groundbreaking method employing deep neural networks to predict the memorability of face photographs. Outperforming previous models, this innovation demonstrates near-human consistency and versatility in handling different face shapes, with potential applications spanning social media, advertising, education, security, and entertainment.
Researchers present CrisisViT, a novel transformer-based model designed for automatic image classification in crisis response scenarios. Leveraging in-domain learning with the Incidents1M crisis image dataset, CrisisViT outperforms conventional models, offering enhanced accuracy in disaster type, image relevance, humanitarian category, and damage severity classification. This innovation provides an efficient solution for crisis responders, enabling rapid image analysis through smartphones and social media, thereby aiding timely decision-making during emergencies.
In this article, researchers unveil a cutting-edge gearbox fault diagnosis method. Leveraging transfer learning and a lightweight channel attention mechanism, the proposed EfficientNetV2-LECA model showcases superior accuracy, achieving over 99% classification accuracy in both gear and bearing samples. The study signifies a pivotal leap in intelligent fault diagnosis for mechanical equipment, addressing challenges posed by limited samples and varying working conditions.
Researchers present a meta-imager using metasurfaces for optical convolution, offloading computationally intensive operations into high-speed, low-power optics. The system employs angular and polarization multiplexing, achieving both positive and negative valued convolution operations simultaneously, showcasing potential in compact, lightweight, and power-efficient machine vision systems.
Researchers have unveiled innovative methods, utilizing lidar data and AI techniques, to precisely delineate river channels' bankfull extents. This groundbreaking approach streamlines large-scale topographic analyses, offering efficiency in flood risk mapping, stream rehabilitation, and tracking channel evolution, marking a significant leap in environmental mapping workflows.
This article covers breakthroughs and innovations in natural language processing, computer vision, and data security. From addressing logical reasoning challenges with the discourse graph attention network to advancements in text classification using BERT models, lightweight mask detection in computer vision, sports analytics employing network graph theory, and data security through image steganography, the authors showcase the broad impact of AI across various domains.
This paper delves into the transformative impact of machine learning (ML) in scientific research while highlighting critical challenges, particularly in COVID-19 diagnostics using AI-driven algorithms. The study underscores concerns about misleading claims, flawed methodologies, and the need for standardized guidelines to ensure credibility and reproducibility. It addresses issues such as data leakage, inadequate reporting, and overstatement of findings, emphasizing the importance of proper training and standardized methodologies in the rapidly evolving field of health-related ML.
This research explores Unique Feature Memorization (UFM) in deep neural networks (DNNs) trained for image classification tasks, where networks memorize specific features occurring only once in a single sample. The study introduces methods, including the M score, to measure and identify UFM, highlighting its privacy implications and potential risks for model robustness. The findings emphasize the need for mitigation strategies to address UFM and enhance the privacy and generalization of DNNs, especially in fields like medical imaging and computer vision.
Terms
While we only use edited and approved content for Azthena
answers, it may on occasions provide incorrect responses.
Please confirm any data provided with the related suppliers or
authors. We do not provide medical advice, if you search for
medical information you must always consult a medical
professional before acting on any information provided.
Your questions, but not your email details will be shared with
OpenAI and retained for 30 days in accordance with their
privacy principles.
Please do not ask questions that use sensitive or confidential
information.
Read the full Terms & Conditions.