TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Methods/EfficientNetV2

EfficientNetV2

Computer VisionIntroduced 200043 papers
Source Paper

Description

EfficientNetV2 is a type convolutional neural network that has faster training speed and better parameter efficiency than previous models. To develop these models, the authors use a combination of training-aware neural architecture search and scaling, to jointly optimize training speed. The models were searched from the search space enriched with new ops such as Fused-MBConv.

Architecturally the main differences are:

  • EfficientNetV2 extensively uses both MBConv and the newly added fused-MBConv in the early layers.
  • EfficientNetV2 prefers smaller expansion ratio for MBConv since smaller expansion ratios tend to have less memory access overhead.
  • EfficientNetV2 prefers smaller 3x3 kernel sizes, but it adds more layers to compensate the reduced receptive field resulted from the smaller kernel size.
  • EfficientNetV2 completely removes the last stride-1 stage in the original EfficientNet, wperhaps due to its large parameter size and memory access overhead.

Papers Using This Method

EfficientFER: EfficientNetv2 Based Deep Learning Approach for Facial Expression Recognition2025-06-02Deep Learning-Based Breast Cancer Detection in Mammography: A Multi-Center Validation Study in Thai Population2025-05-29Comparative Analysis of Lightweight Deep Learning Models for Memory-Constrained Devices2025-05-06Local Herb Identification Using Transfer Learning: A CNN-Powered Mobile Application for Nepalese Flora2025-05-04An improved EfficientNetV2 for garbage classification2025-03-27Deep Learning-based Compression Detection for explainable Face Image Quality Assessment2025-01-07PyPotteryLens: An Open-Source Deep Learning Framework for Automated Digitisation of Archaeological Pottery Documentation2024-12-16A Novel Ensemble-Based Deep Learning Model with Explainable AI for Accurate Kidney Disease Diagnosis2024-12-12Multispecies Animal Re-ID Using a Large Community-Curated Dataset2024-12-07Enhancing AI microscopy for foodborne bacterial classification via adversarial domain adaptation across optical and biological variability2024-11-29SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers2024-11-14Breast Cancer Histopathology Classification using CBAM-EfficientNetV2 with Transfer Learning2024-10-29Enhanced Infield Agriculture with Interpretable Machine Learning Approaches for Crop Classification2024-08-22Toward Enhancing Vehicle Color Recognition in Adverse Conditions: A Dataset and Benchmark2024-08-21Hierarchical Object Detection and Recognition Framework for Practical Plant Disease Diagnosis2024-07-25Analysis of Modern Computer Vision Models for Blood Cell Classification2024-06-30CNN Based Flank Predictor for Quadruped Animal Species2024-06-19CNN-LSTM and Transfer Learning Models for Malware Classification based on Opcodes and API Calls2024-05-04Managing Household Waste through Transfer Learning2024-01-27Unveiling the Human-like Similarities of Automatic Facial Expression Recognition: An Empirical Exploration through Explainable AI2024-01-22