Methods › Computer Vision › Convolutional Neural Networks › EfficientNetV2
EfficientNetV2
Introduced by Mingxing Tan et al. in EfficientNetV2: Smaller Models and Faster Training
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
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.
In Syntology verified reference implementation at level V3; retrieve with get_reference_implementation(name='EfficientNetV2'). This answer is about arXiv:2104.00298, the paper the archive credits with this method.
Origin paper of this answer, arXiv:2104.00298 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 55 ran (of which 14 constructed an object rather than computing a result; 43 with no instrument failure: 11 honoured, 0 violated, 32 with no contract checked; 12 where Syntology's instrument failed) · 24 unverified (of 79 harvested samples) · 13 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).
Papers archive 2025-07-28
archive papers tagged: 43 · with a code link: 17 · where Syntology ran a sample: 2 (2 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (2 of 43 tagged: 2 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 43 of 43, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
EfficientFER: EfficientNetv2 Based Deep Learning Approach for Facial Expression Recognition 2 Jun 2025 · 1 repository
-
Deep Learning-Based Breast Cancer Detection in Mammography: A Multi-Center Validation Study in Thai Population 29 May 2025 · 0 repositories · arXiv:2506.03177
-
Comparative Analysis of Lightweight Deep Learning Models for Memory-Constrained Devices 6 May 2025 · 0 repositories · arXiv:2505.03303
-
Local Herb Identification Using Transfer Learning: A CNN-Powered Mobile Application for Nepalese Flora 4 May 2025 · 0 repositories · arXiv:2505.02147
-
An improved EfficientNetV2 for garbage classification 27 Mar 2025 · 0 repositories · arXiv:2503.21208
-
Deep Learning-based Compression Detection for explainable Face Image Quality Assessment 7 Jan 2025 · 2 repositories · arXiv:2501.03619
-
PyPotteryLens: An Open-Source Deep Learning Framework for Automated Digitisation of Archaeological Pottery Documentation 16 Dec 2024 · 0 repositories · arXiv:2412.11574
-
A Novel Ensemble-Based Deep Learning Model with Explainable AI for Accurate Kidney Disease Diagnosis 12 Dec 2024 · 0 repositories · arXiv:2412.09472
-
Multispecies Animal Re-ID Using a Large Community-Curated Dataset 7 Dec 2024 · 1 repository · arXiv:2412.05602
-
Enhancing AI microscopy for foodborne bacterial classification via adversarial domain adaptation across optical and biological variability 29 Nov 2024 · 0 repositories · arXiv:2411.19514
-
SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers 14 Nov 2024 · 1 repository · arXiv:2411.09420
-
Breast Cancer Histopathology Classification using CBAM-EfficientNetV2 with Transfer Learning 29 Oct 2024 · 0 repositories · arXiv:2410.22392
-
Enhanced Infield Agriculture with Interpretable Machine Learning Approaches for Crop Classification 22 Aug 2024 · 0 repositories · arXiv:2408.12426
-
Toward Enhancing Vehicle Color Recognition in Adverse Conditions: A Dataset and Benchmark 21 Aug 2024 · 1 repository · arXiv:2408.11589
-
Hierarchical Object Detection and Recognition Framework for Practical Plant Disease Diagnosis 25 Jul 2024 · 0 repositories · arXiv:2407.17906
-
Analysis of Modern Computer Vision Models for Blood Cell Classification 30 Jun 2024 · 1 repository · arXiv:2407.00759
-
CNN Based Flank Predictor for Quadruped Animal Species 19 Jun 2024 · 0 repositories · arXiv:2406.13588
-
CNN-LSTM and Transfer Learning Models for Malware Classification based on Opcodes and API Calls 4 May 2024 · 0 repositories · arXiv:2405.02548
-
Managing Household Waste through Transfer Learning 27 Jan 2024 · 1 repository · arXiv:2402.09437
-
Unveiling the Human-like Similarities of Automatic Facial Expression Recognition: An Empirical Exploration through Explainable AI 22 Jan 2024 · 1 repository · arXiv:2401.11835
-
Concrete Surface Crack Detection with Convolutional-based Deep Learning Models 13 Jan 2024 · 0 repositories · arXiv:2401.07124
-
Data Augmentation Techniques for Cross-Domain WiFi CSI-based Human Activity Recognition 1 Jan 2024 · 1 repository · arXiv:2401.00964
-
Directional Antenna Systems for Long-Range Through-Wall Human Activity Recognition 1 Jan 2024 · 1 repository · arXiv:2401.01388
-
Trainwreck: A damaging adversarial attack on image classifiers 24 Nov 2023 · 1 repository · arXiv:2311.14772
-
Hybrid Inception Architecture with Residual Connection: Fine-tuned Inception-ResNet Deep Learning Model for Lung Inflammation Diagnosis from Chest Radiographs 4 Oct 2023 · 0 repositories · arXiv:2310.02591
-
Training Latency Minimization for Model-Splitting Allowed Federated Edge Learning 21 Jul 2023 · 0 repositories · arXiv:2307.11532
-
Modular Multimodal Machine Learning for Extraction of Theorems and Proofs in Long Scientific Documents (Extended Version) 18 Jul 2023 · 2 repositories · arXiv:2307.09047
-
UPSCALE: Unconstrained Channel Pruning 17 Jul 2023 · 1 repository · arXiv:2307.08771Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified (of 7 harvested samples) · 7 pointer-only (licence)
-
Building and Road Segmentation Using EffUNet and Transfer Learning Approach 8 Jul 2023 · 0 repositories · arXiv:2307.03980
-
Deep Learning Applications Based on WISE Infrared Data: Classification of Stars, Galaxies and Quasars 17 May 2023 · 0 repositories · arXiv:2305.10217
-
EfficientTempNet: Temporal Super-Resolution of Radar Rainfall 9 Mar 2023 · 0 repositories · arXiv:2303.05552
-
SleepyWheels: An Ensemble Model for Drowsiness Detection leading to Accident Prevention 1 Nov 2022 · 0 repositories · arXiv:2211.00718
-
DARE: A large-scale handwritten date recognition system 2 Oct 2022 · 0 repositories · arXiv:2210.00503
-
Cross-Forgery Analysis of Vision Transformers and CNNs for Deepfake Image Detection 28 Jun 2022 · 2 repositories · arXiv:2206.13829
-
Bag of Tricks for Long-Tail Visual Recognition of Animal Species in Camera-Trap Images 24 Jun 2022 · 1 repository · arXiv:2206.12458
-
Gaze-Guided Class Activation Mapping: Leveraging Human Attention for Network Attention in Chest X-rays Classification 15 Feb 2022 · 0 repositories · arXiv:2202.07107
-
The self-supervised spectral-spatial attention-based transformer network for automated, accurate prediction of crop nitrogen status from UAV imagery 12 Nov 2021 · 0 repositories · arXiv:2111.06839
-
Automated Channel Pruning with Learned Importance 29 Sep 2021 · 0 repositories
-
Hardware-Aware Network Transformation 29 Sep 2021 · 0 repositories
-
DEM Super-Resolution with EfficientNetV2 20 Sep 2021 · 0 repositories · arXiv:2109.09661
-
LANA: Latency Aware Network Acceleration 12 Jul 2021 · 0 repositories · arXiv:2107.10624
-
Solution for Large-scale Long-tailed Recognition with Noisy Labels 20 Jun 2021 · 1 repository · arXiv:2106.10683
-
EfficientNetV2: Smaller Models and Faster Training 1 Apr 2021 · 26 repositories · arXiv:2104.00298Syntology official (archive's flag): 1 ran · 55 ran (of which 14 constructed an object rather than computing a result; 43 with no instrument failure: 11 honoured, 0 violated, 32 with no contract checked; 12 where Syntology's instrument failed) · 24 unverified (of 79 harvested samples) · 13 pointer-only (licence)
Tasks archive 2025-07-28
20 shown of 65 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections