Human Posture Recognition and Estimation Method Based on 3D Multiview Basketball Sports Dataset by Xuhui Song, Linyuan Fan

“…The convolutional neural network framework used in this research is VGG11, and the basketball dataset Image Net is used for pretraining. This research uses some modules of the VGG11 network. …”
Get full text

Mining label-free consistency regularization for noisy facial expression recognition by Yumei Tan, Haiying Xia, Shuxiang Song

“…Moreover, MCR demonstrates superior generalization capability on other datasets with noisy labels, such as CIFAR100 and Tiny-ImageNet.…”
Get full text

IMViT: Adjacency Matrix-Based Lightweight Plain Vision Transformer by Qihao Chen, Yunfeng Yan, Xianbo Wang, Jishen Peng

“…Extensive experiments show that the proposed lightweight IMViT-B outperforms DeiTIII, this paper IMViT-B(300 epochs) achieves a top accuracy of <inline-formula> <tex-math notation="LaTeX">$82.8~\%$ </tex-math></inline-formula> on ImageNet-1K with only 26M parameters, surpasses the DeiTIII-S(800 epochs) +1.4%, with a similar number of parameters and computation cost. …”
Get full text

Convolutional Neural Network Compression via Dynamic Parameter Rank Pruning by Manish Sharma, Jamison Heard, Eli Saber, Panagiotis Markopoulos

“…We evaluate our method on modern CNNs, including ResNet-18, ResNet-20, and ResNet-32, using datasets like CIFAR-10, CIFAR-100, and ImageNet (2012). Our experiments demonstrate that the proposed method can reduce model parameters by up to 50% and improve classification accuracy by up to 2% over baseline models, making CNNs more feasible for practical applications.…”
Get full text

You Only Attack Once: Single-Step DeepFool Algorithm by Jun Li, Yanwei Xu, Yaocun Hu, Yongyong Ma, Xin Yin

“…Furthermore, we performed data visualization on the ImageNet dataset, demonstrating that the proposed algorithm focuses more on attacking important features. …”
Get full text

SViG: A Similarity-Thresholded Approach for Vision Graph Neural Networks by Ismael Elsharkawi, Hossam Sharara, Ahmed Rafea

“…We show that our proposed method can achieve higher performance than the ViG model for image classification on the benchmark ImageNet-1K dataset, without increasing the complexity of the model. …”
Get full text

Abnormality detection in nailfold capillary images using deep learning with EfficientNet and cascade transfer learning by Mona Ebadi Jalal, Omar S. Emam, Cristián Castillo-Olea, Begoña García-Zapirain, Adel Elmaghraby

“…The results demonstrate that pre-trained EfficientNet-B0 on the ImageNet dataset, followed by transfer learning from domain-specific classes, significantly enhances the classifier’s performance in distinguishing between Normal and Abnormal classes. …”
Get full text

Research on Arthroscopic Images Bleeding Detection Algorithm Based on ViT-ResNet50 Integrated Model and Transfer Learning by Zewen Liu, Shaoyi Zhou, Jianqiao Chu, Zhiyuan Chai, Dongdong Chang, Yi Yuan, Jinling Qin, Xiancheng Wang

“…Firstly, Vision Transformer model and ResNet50 model are used to learn features by transfer learning on ImageNet dataset respectively. Then, a difference-enhanced proportional sampling method is proposed to enhance the unbalanced data. …”
Get full text

基于迁移学习的中国蛇类识别研究 by 周志斌 罗志聪 张展榜 孙奇燕

“…针对蛇类识别任务的特点,提出改进方案:根据蛇类形态特点,采用合适的数据增强方式扩充数据集; 对神经网络模型进行改进,以适应蛇类图像分类任务; 训练中采用Adam优化算法,优化模型学习过程; 采用迁移学习方式,利用ImageNet数据集上训练得到的权值对模型初始化,并进行微调训练提升模型对蛇类识别任务的高阶特征表达能力。…”
Get full text

Adapting to evolving MRI data: A transfer learning approach for Alzheimer’s disease prediction by Rosanna Turrisi, Sarthak Pati, Giovanni Pioggia, Gennaro Tartarisco

“…This study explores Transfer Learning (TL) approaches to enhance AD diagnosis using a Baseline model consisting of a 3D-Convolutional Neural Network trained on 80 3T MRI scans.Two scenarios are explored: (A) utilizing historical data to address changes in MRI acquisitions (from 1.5T to 3T MRI), and (B) adapting 2D models pre-trained on ImageNet (ResNet18, ResNet50, ResNet101) for 3D image processing when historical data is unavailable. …”
Get full text

酶消化法结合人工智能技术在法医学溺死硅藻检验中的应用 by 于慧潇, 朱永正, 赵天琦, 程奇, 李周儒, 殷文江, 陈敏, 蔡红星

“…方法收集6例溺死尸体的肺组织进行蛋白酶K消解并制成涂片，利用数字化图像矩阵切割方法将涂片进行数字化处理并据此建立硅藻-背景数据库，将数据集按照3：1：1的比例分为训练集、验证集和测试集，在ImageNet预训练基础上对卷积神经网络（CNN）模型进行训练和内部验证及外部测试。结果结果显示最佳模型外部测试的准确率达97.65%，且模型特征提取区域即为硅藻所在区域。…”
Get full text

Voice analysis and deep learning for detecting mental disorders in pregnant women: a cross-sectional study by Hikaru Ooba, Jota Maki, Hisashi Masuyama

“…The EfficientFormer V2-L model, pretrained on ImageNet, was employed with transfer learning for classification. …”
Get full text

Fully Automated Bone Age Assessment on Large-Scale Hand X-Ray Dataset by Xiaoying Pan, Yizhe Zhao, Hao Chen, De Wei, Chen Zhao, Zhi Wei

“…To optimize the learning process, we employ six off-the-shell deep Convolutional Neural Networks (CNNs) with pretrained weights on ImageNet. We use them to extract features of preprocessed hand images with a transfer learning technique. …”
Get full text

Enhancing cardiac diagnostics: a deep learning ensemble approach for precise ECG image classification by Ahmed Alsayat, Alshimaa Abdelraof Mahmoud, Saad Alanazi, Ayman Mohamed Mostafa, Nasser Alshammari, Majed Abdullah Alrowaily, Hosameldeen Shabana, Mohamed Ezz

“…In the first experiment, eight distinct neural network models were selected based on their top-5 accuracy on the ImageNet validation dataset and were fine-tuned using transfer learning techniques. …”
Get full text

A novel lightweight model for tea disease classification based on feature reuse and channel focus attention mechanism by Junjie Liang, Renjie Liang, Dongxia Wang

“…Experimental results across self-built tea disease datasets, Mini-ImageNet, and PlantVillage datasets show LTDDN outperforms classic CNN, lightweight CNN, and popular ViT models in recognition accuracy. …”
Get full text

Визначення віку людини за фото на основі нейронних мереж by Євгеній Вербенко, Ольга Мацуга

“…Ці архітектури згорткових нейронних мереж показали значні досягнення в класифікації зображень на наборі даних ImageNet. AlexNet впровадив використання ReLU-активації, dropout та max-pooling, тоді як VGG-19 підкреслив глибші архітектури з малими фільтрами. …”
Get full text

Modality Specific CBAM-VGGNet Model for the Classification of Breast Histopathology Images via Transfer Learning by Areesha Ijaz, Basit Raza, Iqra Kiran, Abdul Waheed, Aadil Raza, Habib Shah, Sulaiman Aftan

“…Instead of using pre-trained models on ImageNet, we have trained VGG16 and VGG19 models on the same domain cancerous histopathology datasets, which are then used as fixed feature extractors. …”
Get full text

Employing the concept of stacking ensemble learning to generate deep dream images using multiple CNN variants by Lafta Alkhazraji, Ayad R. Abbas, Abeer S. Jamil, Zahraa Saddi Kadhim, Wissam Alkhazraji, Sabah Abdulazeez Jebur, Bassam Noori Shaker, Mohammed Abdallazez Mohammed, Mohanad A. Mohammed, Basim Mohammed Al-Araji, Abdulkareem Z. Mohmmed, Wasiq Khan, Bilal Khan, Abir Jaafar Hussain

“…The resulting dream-like images contain shapes that reflect elements from the ImageNet dataset on which the above pre-trained models were trained. …”
Get full text

E-MAC: Enhanced In-SRAM MAC Accuracy via Digital-to-Time Modulation by Saeed Seyedfaraji, Salar Shakibhamedan, Amire Seyedfaraji, Baset Mesgari, Nima Taherinejad, Axel Jantsch, Semeen Rehman

“…., a 0.1% and 0.17% reduction for LeNet5-based CNN and VGG16, respectively, when trained on the MNIST and ImageNet datasets.…”
Get full text

Co-Optimization of Power Delivery Network Design for 3-D Heterogeneous Integration of RRAM-Based Compute In-Memory Accelerators by Madison Manley, James Read, Ankit Kaul, Shimeng Yu, Muhannad Bakir

“…Using our framework, we model IR-drop and simulate its impact on the accuracy of ResNet-50 and ResNet-152 when classifying images from the ImageNet 1k dataset in the presence of injected PVT noise. …”
Get full text