MobileNetV2
PulseAugur coverage of MobileNetV2 — every cluster mentioning MobileNetV2 across labs, papers, and developer communities, ranked by signal.
- instance of VGG19 90%
- instance of ResNet18 70%
- instance of EfficientNet B0 70%
- used by alphaXiv 70%
- uses EfficientNet B0 70%
- instance of ResNet-50 70%
- used by ScienceCast 70%
- instance of ResNet-18 70%
- used by Gotit.pub 70%
- competes with Vgg16 70%
- competes with ResNet-50 70%
- used by EfficientNet B0 60%
7 day(s) with sentiment data
-
Federated learning system FedXCrop enhances privacy in crop disease detection
Researchers have developed FedXCrop, a federated learning system designed for privacy-preserving crop disease detection. This system allows for the training of disease classification models without farms needing to shar…
-
Low-cost AgriDefend device uses AI to detect crop stress before symptoms appear
Researchers have developed AgriDefend, a low-cost offline edge device designed to detect crop stress before visible symptoms appear. This device fuses data from canopy imagery analyzed by a MobileNetV2 neural network an…
-
Deep learning models benchmarked for breast cancer diagnosis
Researchers have evaluated ten deep learning models, including CNNs like DenseNet121 and transformer models such as ViT and Swin Transformer, for their effectiveness in diagnosing breast cancer from medical images. Dens…
-
New compute-in-memory engine boosts CNN inference efficiency
Researchers have developed SLICE-CiM, a novel control engine for SRAM-based compute-in-memory (CIM) macros designed to enhance energy efficiency in CNN inference. The system incorporates four peripheral blocks, includin…
-
New personalized federated learning method HDC-FL shows strong performance
Researchers have introduced HDC-FL, a novel method for personalized federated learning that leverages client-specific classifier heads to guide representation sharing. This approach groups client descriptors and creates…
-
New research examines deepfake detection using AI models and human performance
Two new research papers explore the detection of deepfake images, with one paper evaluating deep learning models and the other focusing on human performance. The first study compared a model trained from scratch against…
-
New research explores advanced quantization for edge AI accelerators
Two new research papers explore advanced quantization techniques for deep neural networks (DNNs) on edge devices. The first paper introduces ShiftQAT, a quantization-aware training flow for the MAX7800x family of CNN ac…
-
CNNs show promise for detecting plant diseases in Ethiopia and Brazil
Researchers are exploring the use of convolutional neural networks (CNNs) for agricultural disease detection in different plant species. One study developed a lightweight CNN to identify potato leaf diseases in Ethiopia…
-
New integer-only training method slashes neural network memory use
Researchers have developed a novel training algorithm for deep neural networks that exclusively uses integer arithmetic, eliminating the need for floating-point operations in any stage of the training process. This meth…
-
New deep learning patching method balances performance and training time
A new paper introduces Stride Independent Patching (SSP), a semi-automatic method for positioning image patches in deep learning. Unlike automatic stride-dependent methods, SSP relies on user input to define patch locat…
-
Contrast enhancement boosts cervical cancer classification accuracy in CNNs
A new research paper published on arXiv explores the effectiveness of image preprocessing techniques for improving cervical cancer classification using deep learning models. The study evaluated two methods, a PMD filter…
-
Crop yield prediction study reveals critical data validation flaws
A research paper on crop yield prediction for Punjab, Pakistan, highlights significant issues with data validation and model performance. The study developed a prototype combining tree-ensemble models and a leaf-health …
-
New OCR methods boost recognition for handwritten Bangla texts · 2 sources tracked
Researchers have developed new methods for optical character recognition (OCR) specifically for handwritten Bangla texts. One study focuses on word recognition using deep learning models like SSD with MobileNetV2 and Fa…
-
FPGA platform accelerates approximate multiplier evaluation for DNNs
Researchers have developed FAME, a new platform utilizing FPGAs to accelerate the evaluation of approximate multipliers for deep neural networks. This hardware-based approach significantly reduces the time needed to ass…
-
New Edge Intelligence Framework FREDI Optimizes Resource Allocation and Inference
This paper introduces FREDI, a framework for secure edge intelligence that optimizes resource allocation and inference for cooperative multi-layer systems. FREDI employs dual confidence thresholds for early-exit CNN scr…
-
New multi-exit TinyML scheme boosts edge AI efficiency
Researchers have developed a novel multi-exit computational scheme for TinyML systems on edge devices, aiming to improve energy efficiency and real-time performance. This approach, deployed on a GWT GAP9 System-on-Chip,…
-
Machine learning tackles waste management and health risks in Ghana
A new study explores the use of machine learning to address solid waste management issues in Ghana. Researchers developed a Random Forest classifier to predict illness categories based on waste disposal practices and de…
-
Lightweight ML framework offers interpretable malaria diagnosis
Researchers have developed EMFE, a new machine learning framework designed for malaria cell classification. Unlike current deep learning models that are accurate but resource-intensive and opaque, EMFE utilizes a five-f…
-
Adaptive AI task partitioning framework reduces latency and energy use
Researchers have developed a novel framework for dynamically partitioning and offloading AI tasks across a heterogeneous edge-cloud continuum. This adaptive approach, evaluated on real hardware including a Raspberry Pi,…
-
New AQUA20 dataset targets challenging underwater species classification
Researchers have introduced AQUA20, a new benchmark dataset designed to improve underwater species classification. The dataset contains 8,171 images of 20 marine species, specifically curated to address challenges like …