ResNet50
PulseAugur coverage of ResNet50 — every cluster mentioning ResNet50 across labs, papers, and developer communities, ranked by signal.
4 天有情绪数据
-
深度学习集成提高了植物病害分类的准确性
研究人员开发了AgriMind，一个用于自动化植物病害分类的集成深度学习框架。该系统结合了三种模型——ResNet50、EfficientNet-B0和DenseNet121——这些模型在超过20,000张辣椒、土豆和番茄植物的图像上进行了训练。该集成模型达到了99.23%的准确率，与单个模型相比显著降低了错误率，并展示了在GPU上高效的处理速度。
-
Gemini Embeddings Outperform ResNet50, SigLIP in Visual Recommendations
This article explores the effectiveness of Gemini multimodal embeddings for visual recommendation systems. It presents a comparative analysis of Gemini against ResNet50 and SigLIP, evaluating their performance in buildi…
-
Diffusion augmentation boosts Bangla character recognition accuracy
Researchers have developed a confidence-guided diffusion augmentation method to improve the recognition of handwritten Bangla compound characters. This approach uses diffusion models to generate high-quality synthetic c…
-
New OUIDecay method adapts CNN regularization layer-by-layer
Researchers have introduced OUIDecay, a novel adaptive weight decay method for convolutional neural networks. This technique dynamically adjusts regularization strength for each layer based on online activation patterns…
-
LC4-DViT uses generative AI and transformers for accurate land-cover mapping
Researchers have developed LC4-DViT, a novel framework for land-cover classification using a deformable Vision Transformer. This approach combines generative data creation with a deformation-aware backbone to improve ac…
-
New DEEP-GAP study compares NVIDIA T4 and L4 GPU inference performance
A new research paper introduces DEEP-GAP, a methodology for evaluating GPU inference performance. The study systematically compares the NVIDIA T4 and L4 GPUs using various deep learning models and precision modes. Resul…
-
AI models show strong breast density prediction from ultrasounds, generalize well
Researchers externally validated three deep learning models—DenseNet121, ViT-B/32, and ResNet50—for predicting breast density from ultrasound images. The models demonstrated strong performance, particularly in extremely…
-
研究人员开发用于图像分类和分割的新型无监督域自适应框架
研究人员开发了新的无监督域自适应（UDA）框架，以应对将在一个数据集上训练的AI模型应用于不同、未标记数据集的挑战。一种方法利用了两个基础模型，特别是Segment Anything Model (SAM) 和 DINOv3，通过从更广泛的目标像素中学习并构建稳定、域不变的原型来改进语义分割。另一个框架专注于医学成像，采用面向方向的自适应技术对多模态MRI的脑肿瘤进行分类，并使用RKHS-MMD对X射线胸片分类进行鲁棒自适应，从而减少…
-
New papers explore fake image detection and vision model interpretation
Two new research papers explore advancements in interpreting and evaluating deep learning models. One paper details a comparative study of four CNN architectures for detecting fake images, with VGG16 achieving the highe…
-
New architecture tackles rare animal image classification with adaptive DCT and hybrid backbones
A research paper introduces a novel deep-learning architecture designed to improve image classification accuracy for rare animal species, where data is inherently scarce. The proposed hybrid framework combines an adapti…
-
研究人员结合 DPU 和 GPU 以加速神经网络推理
研究人员开发了一种新颖的方法，通过在深度学习处理单元 (DPU) 和图形处理单元 (GPU) 之间拆分卷积神经网络 (CNN) 计算来加速神经网络推理。这种“拆分 CNN 推理”方法在数据源附近的 DPU 上处理初始层，在 GPU 上处理后续层，从而显著降低延迟。还引入了一个图神经网络 (GNN) 模型，以准确预测各种 CNN 架构的最佳层划分，准确率达到 96.27%。
-
HFS-TriNet network improves prostate cancer classification from TRUS videos
Researchers have developed HFS-TriNet, a novel network designed to improve prostate cancer classification from transrectal ultrasound (TRUS) videos. This method addresses challenges in TRUS video analysis, such as redun…