{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/efficientnetv2","slug":"efficientnetv2","name":"EfficientNetV2","full_name":"EfficientNetV2","full_name_withheld":false,"description_markdown":"**EfficientNetV2** is a type convolutional neural network that has faster training speed and better parameter efficiency than [previous models](https://paperswithcode.com/method/efficientnet). To develop these models, the authors use a combination of training-aware [neural architecture search](https://paperswithcode.com/method/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](https://ai.googleblog.com/2019/08/efficientnet-edgetpu-creating.html).\r\n\r\nArchitecturally the main differences are:\r\n\r\n- EfficientNetV2 extensively uses both [MBConv](https://paperswithcode.com/method/inverted-residual-block)  and the newly added fused-MBConv in the early layers.\r\n- EfficientNetV2 prefers smaller expansion ratio for [MBConv](https://paperswithcode.com/method/inverted-residual-block) since smaller expansion ratios tend to have less memory access overhead.\r\n- EfficientNetV2 prefers smaller 3x3 kernel sizes, but it adds more layers to compensate the reduced receptive field resulted from the smaller kernel size. \r\n- EfficientNetV2 completely removes the last stride-1 stage in the original EfficientNet, wperhaps due to its large parameter size and memory access overhead.","description_state":"present","introduced_year":null,"introduced_by":{"title":"EfficientNetV2: Smaller Models and Faster Training","paper":"/paper/efficientnetv2-smaller-models-and-faster","first_author":"Mingxing Tan","n_authors":2,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/efficientnetv2-smaller-models-and-faster"},"source":{"url":"https://arxiv.org/abs/2104.00298v3","title":"EfficientNetV2: Smaller Models and Faster Training","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Convolutional Neural Networks","url":"/methods/category/convolutional-neural-networks","pwc_aliases":[]}],"n_papers_tagged":43,"archive_num_papers":43,"papers_newest_first":[{"paper":"/paper/efficientfer-efficientnetv2-based-deep","slug":"efficientfer-efficientnetv2-based-deep","title":"EfficientFER: EfficientNetv2 Based Deep Learning Approach for Facial Expression Recognition","date":"2025-06-02","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"2506-03177","title":"Deep Learning-Based Breast Cancer Detection in Mammography: A Multi-Center Validation Study in Thai Population","date":"2025-05-29","arxiv_id":"2506.03177","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparative-analysis-of-lightweight-deep","title":"Comparative Analysis of Lightweight Deep Learning Models for Memory-Constrained Devices","date":"2025-05-06","arxiv_id":"2505.03303","n_code_links":0,"syntology":null},{"paper":null,"slug":"local-herb-identification-using-transfer","title":"Local Herb Identification Using Transfer Learning: A CNN-Powered Mobile Application for Nepalese Flora","date":"2025-05-04","arxiv_id":"2505.02147","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-improved-efficientnetv2-for-garbage","title":"An improved EfficientNetV2 for garbage classification","date":"2025-03-27","arxiv_id":"2503.21208","n_code_links":0,"syntology":null},{"paper":"/paper/deep-learning-based-compression-detection-for","slug":"deep-learning-based-compression-detection-for","title":"Deep Learning-based Compression Detection for explainable Face Image Quality Assessment","date":"2025-01-07","arxiv_id":"2501.03619","n_code_links":2,"syntology":null},{"paper":null,"slug":"pypotterylens-an-open-source-deep-learning","title":"PyPotteryLens: An Open-Source Deep Learning Framework for Automated Digitisation of Archaeological Pottery Documentation","date":"2024-12-16","arxiv_id":"2412.11574","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-novel-ensemble-based-deep-learning-model","title":"A Novel Ensemble-Based Deep Learning Model with Explainable AI for Accurate Kidney Disease Diagnosis","date":"2024-12-12","arxiv_id":"2412.09472","n_code_links":0,"syntology":null},{"paper":"/paper/multispecies-animal-re-id-using-a-large","slug":"multispecies-animal-re-id-using-a-large","title":"Multispecies Animal Re-ID Using a Large Community-Curated Dataset","date":"2024-12-07","arxiv_id":"2412.05602","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhancing-ai-microscopy-for-foodborne","title":"Enhancing AI microscopy for foodborne bacterial classification via adversarial domain adaptation across optical and biological variability","date":"2024-11-29","arxiv_id":"2411.19514","n_code_links":0,"syntology":null},{"paper":"/paper/sag-vit-a-scale-aware-high-fidelity-patching","slug":"sag-vit-a-scale-aware-high-fidelity-patching","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","date":"2024-11-14","arxiv_id":"2411.09420","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficientnet-with-hybrid-attention-mechanisms","title":"Breast Cancer Histopathology Classification using CBAM-EfficientNetV2 with Transfer Learning","date":"2024-10-29","arxiv_id":"2410.22392","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhanced-infield-agriculture-with","title":"Enhanced Infield Agriculture with Interpretable Machine Learning Approaches for Crop Classification","date":"2024-08-22","arxiv_id":"2408.12426","n_code_links":0,"syntology":null},{"paper":"/paper/toward-enhancing-vehicle-color-recognition-in","slug":"toward-enhancing-vehicle-color-recognition-in","title":"Toward Enhancing Vehicle Color Recognition in Adverse Conditions: A Dataset and Benchmark","date":"2024-08-21","arxiv_id":"2408.11589","n_code_links":1,"syntology":null},{"paper":null,"slug":"hierarchical-object-detection-and-recognition","title":"Hierarchical Object Detection and Recognition Framework for Practical Plant Disease Diagnosis","date":"2024-07-25","arxiv_id":"2407.17906","n_code_links":0,"syntology":null},{"paper":"/paper/analysis-of-modern-computer-vision-models-for","slug":"analysis-of-modern-computer-vision-models-for","title":"Analysis of Modern Computer Vision Models for Blood Cell Classification","date":"2024-06-30","arxiv_id":"2407.00759","n_code_links":1,"syntology":null},{"paper":null,"slug":"cnn-based-flank-predictor-for-quadruped","title":"CNN Based Flank Predictor for Quadruped Animal Species","date":"2024-06-19","arxiv_id":"2406.13588","n_code_links":0,"syntology":null},{"paper":null,"slug":"cnn-lstm-and-transfer-learning-models-for","title":"CNN-LSTM and Transfer Learning Models for Malware Classification based on Opcodes and API Calls","date":"2024-05-04","arxiv_id":"2405.02548","n_code_links":0,"syntology":null},{"paper":"/paper/managing-household-waste-through-transfer","slug":"managing-household-waste-through-transfer","title":"Managing Household Waste through Transfer Learning","date":"2024-01-27","arxiv_id":"2402.09437","n_code_links":1,"syntology":null},{"paper":"/paper/unveiling-the-human-like-similarities-of","slug":"unveiling-the-human-like-similarities-of","title":"Unveiling the Human-like Similarities of Automatic Facial Expression Recognition: An Empirical Exploration through Explainable AI","date":"2024-01-22","arxiv_id":"2401.11835","n_code_links":1,"syntology":null},{"paper":null,"slug":"concrete-surface-crack-detection-with","title":"Concrete Surface Crack Detection with Convolutional-based Deep Learning Models","date":"2024-01-13","arxiv_id":"2401.07124","n_code_links":0,"syntology":null},{"paper":"/paper/data-augmentation-techniques-for-cross-domain","slug":"data-augmentation-techniques-for-cross-domain","title":"Data Augmentation Techniques for Cross-Domain WiFi CSI-based Human Activity Recognition","date":"2024-01-01","arxiv_id":"2401.00964","n_code_links":1,"syntology":null},{"paper":"/paper/directional-antenna-systems-for-long-range","slug":"directional-antenna-systems-for-long-range","title":"Directional Antenna Systems for Long-Range Through-Wall Human Activity Recognition","date":"2024-01-01","arxiv_id":"2401.01388","n_code_links":1,"syntology":null},{"paper":"/paper/trainwreck-a-damaging-adversarial-attack-on","slug":"trainwreck-a-damaging-adversarial-attack-on","title":"Trainwreck: A damaging adversarial attack on image classifiers","date":"2023-11-24","arxiv_id":"2311.14772","n_code_links":1,"syntology":null},{"paper":null,"slug":"hybrid-inception-architecture-with-residual","title":"Hybrid Inception Architecture with Residual Connection: Fine-tuned Inception-ResNet Deep Learning Model for Lung Inflammation Diagnosis from Chest Radiographs","date":"2023-10-04","arxiv_id":"2310.02591","n_code_links":0,"syntology":null},{"paper":null,"slug":"training-latency-minimization-for-model","title":"Training Latency Minimization for Model-Splitting Allowed Federated Edge Learning","date":"2023-07-21","arxiv_id":"2307.11532","n_code_links":0,"syntology":null},{"paper":"/paper/multimodal-machine-learning-for-extraction-of","slug":"multimodal-machine-learning-for-extraction-of","title":"Modular Multimodal Machine Learning for Extraction of Theorems and Proofs in Long Scientific Documents (Extended Version)","date":"2023-07-18","arxiv_id":"2307.09047","n_code_links":2,"syntology":null},{"paper":"/paper/upscale-unconstrained-channel-pruning","slug":"upscale-unconstrained-channel-pruning","title":"UPSCALE: Unconstrained Channel Pruning","date":"2023-07-17","arxiv_id":"2307.08771","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":1,"n_instrument":4,"unverified":2,"pointer_only":7,"phrase":"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","official":{"repos":["apple/ml-upscale"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"building-and-road-segmentation-using-effunet","title":"Building and Road Segmentation Using EffUNet and Transfer Learning Approach","date":"2023-07-08","arxiv_id":"2307.03980","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-applications-based-on-wise","title":"Deep Learning Applications Based on WISE Infrared Data: Classification of Stars, Galaxies and Quasars","date":"2023-05-17","arxiv_id":"2305.10217","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficienttempnet-temporal-super-resolution-of","title":"EfficientTempNet: Temporal Super-Resolution of Radar Rainfall","date":"2023-03-09","arxiv_id":"2303.05552","n_code_links":0,"syntology":null},{"paper":null,"slug":"sleepywheels-an-ensemble-model-for-drowsiness","title":"SleepyWheels: An Ensemble Model for Drowsiness Detection leading to Accident Prevention","date":"2022-11-01","arxiv_id":"2211.00718","n_code_links":0,"syntology":null},{"paper":null,"slug":"dare-a-large-scale-handwritten-date","title":"DARE: A large-scale handwritten date recognition system","date":"2022-10-02","arxiv_id":"2210.00503","n_code_links":0,"syntology":null},{"paper":"/paper/cross-forgery-analysis-of-vision-transformers","slug":"cross-forgery-analysis-of-vision-transformers","title":"Cross-Forgery Analysis of Vision Transformers and CNNs for Deepfake Image Detection","date":"2022-06-28","arxiv_id":"2206.13829","n_code_links":2,"syntology":null},{"paper":"/paper/bag-of-tricks-for-long-tail-visual","slug":"bag-of-tricks-for-long-tail-visual","title":"Bag of Tricks for Long-Tail Visual Recognition of Animal Species in Camera-Trap Images","date":"2022-06-24","arxiv_id":"2206.12458","n_code_links":1,"syntology":null},{"paper":null,"slug":"gaze-guided-class-activation-mapping","title":"Gaze-Guided Class Activation Mapping: Leveraging Human Attention for Network Attention in Chest X-rays Classification","date":"2022-02-15","arxiv_id":"2202.07107","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-channel-spatial-attention-based-vision","title":"The self-supervised spectral-spatial attention-based transformer network for automated, accurate prediction of crop nitrogen status from UAV imagery","date":"2021-11-12","arxiv_id":"2111.06839","n_code_links":0,"syntology":null},{"paper":null,"slug":"automated-channel-pruning-with-learned","title":"Automated Channel Pruning with Learned Importance","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"hardware-aware-network-transformation","title":"Hardware-Aware Network Transformation","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"dem-super-resolution-with-efficientnetv2","title":"DEM Super-Resolution with EfficientNetV2","date":"2021-09-20","arxiv_id":"2109.09661","n_code_links":0,"syntology":null},{"paper":null,"slug":"hant-hardware-aware-network-transformation","title":"LANA: Latency Aware Network Acceleration","date":"2021-07-12","arxiv_id":"2107.10624","n_code_links":0,"syntology":null},{"paper":"/paper/solution-for-large-scale-long-tailed","slug":"solution-for-large-scale-long-tailed","title":"Solution for Large-scale Long-tailed Recognition with Noisy Labels","date":"2021-06-20","arxiv_id":"2106.10683","n_code_links":1,"syntology":null},{"paper":"/paper/efficientnetv2-smaller-models-and-faster","slug":"efficientnetv2-smaller-models-and-faster","title":"EfficientNetV2: Smaller Models and Faster Training","date":"2021-04-01","arxiv_id":"2104.00298","n_code_links":26,"syntology":{"ran":55,"of":79,"n_ran_checked":43,"n_instrument":12,"unverified":24,"pointer_only":13,"phrase":"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","official":{"repos":["google/automl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["community","listed","official"]}}}],"papers_shown":43,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":43,"with_a_code_link":17,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":43,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":2,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":2,"papers_where_code_ran_first_page":"/method/efficientnetv2/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/efficientnetv2/papers/ran/1","json":"/method/efficientnetv2/papers/ran/1.json","rows":2}],"tasks":[{"task":"/task/transfer-learning","name":"Transfer Learning","papers":13},{"task":"/task/image-classification","name":"Image Classification","papers":7},{"task":"/task/classification-1","name":"Classification","papers":6},{"task":"/task/image-classification","name":"image-classification","papers":6},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":5},{"task":"/task/deep-learning","name":"Deep Learning","papers":3},{"task":"/task/diagnostic","name":"Diagnostic","papers":3},{"task":"/task/architecture-search","name":"Neural Architecture Search","papers":3},{"task":"/task/activity-recognition","name":"Activity Recognition","papers":2},{"task":"/task/breast-cancer-detection","name":"Breast Cancer Detection","papers":2},{"task":"/task/computational-efficiency","name":"Computational Efficiency","papers":2},{"task":"/task/edge-computing","name":"Edge-computing","papers":2},{"task":"/task/facial-expression-recognition-1","name":"Facial Expression Recognition","papers":2},{"task":null,"name":"GPU","papers":2},{"task":"/task/human-activity-recognition","name":"Human Activity Recognition","papers":2},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":2},{"task":"/task/super-resolution","name":"Super-Resolution","papers":2},{"task":"/task/adversarial-attack","name":"Adversarial Attack","papers":1},{"task":"/task/animal-pose-estimation","name":"Animal Pose Estimation","papers":1},{"task":"/task/articles","name":"Articles","papers":1}],"tasks_shown":20,"n_tasks":65,"usage_by_year":[{"year":"2021","papers":7},{"year":"2022","papers":5},{"year":"2023","papers":8},{"year":"2024","papers":17},{"year":"2025","papers":6}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/efficientnetv2"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=EfficientNetV2","read_at":"2026-10-05T00:55:31+00:00","query":"EfficientNetV2","kind":"method","have":"verified_code","tier":null,"verified_implementation":true,"level":3,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":{"method":"EfficientNetV2","origin_arxiv_id":"2104.00298"},"resolution":"exact","resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":"same_paper","archive_paper_arxiv_id":"2104.00298","repositories":{"listed":null,"in_graph":25,"list_truncated":null,"strongest_link":null},"retrieve_with":"get_reference_implementation(name='EfficientNetV2')","name_competition":{"verdict":"sole_bearer","may_be_wrong_sense":false,"bearers_found":1,"served":{"arxiv_id":"2104.00298","citations":4783},"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing else in this corpus is named 'EfficientNetV2'. That is a statement about this corpus and not about the field: short names are reused, and a sense we never collected cannot show up here. Confirm `served.arxiv_id` if you had a specific paper in mind."},"name_competition_text":null,"near_matches":null,"code_nearby":[],"code_nearby_caption":null,"origin_paper":{"arxiv_id":"2104.00298","page":"/paper/efficientnetv2-smaller-models-and-faster","syntology_url":"https://syntology.ai/paper/2104.00298","in_graph_layer":true,"samples":79,"ran":55,"n_ran_checked":43,"n_instrument":12,"unverified":24,"phrase":"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","instrument_means":"failures of Syntology's instrument, not of the code"},"line":"verified reference implementation at level V3. This answer is about arXiv:2104.00298, the paper the archive credits with this method.","level_legend":{"state":"quoted","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","card_sha256":"479785a84658dd682a11b10237b3620d651d7f87799f5dc7add970aaa83f6d39","note":"Syntology's served verification levels, quoted verbatim from its MCP server card; a row is split where the card separates clauses with a double hyphen, and the separator is not reproduced","levels":[{"level":"V0","quoted":["imports"]},{"level":"V1","quoted":["executes against a synthesized fixture and returns a value of the recorded type"]},{"level":"V2","quoted":["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)"]},{"level":"V3","quoted":["paper-derived property tests pass on both of those same two generations."]}],"no_rung":"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."}},"syntology_have_state":"loaded","record_sha256":"443aaff8469abfb3756324ebc16f6bab9b20b263f7287690f919c05098e5c47d","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}