Pith. sign in

REVIEW 8 cited by

EfficientNetV2: Smaller Models and Faster Training

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2104.00298 v3 pith:YIS77JEH submitted 2021-04-01 cs.CV

classification cs.CV
keywords modelstrainingefficientnetv2accuracyfasterdropefficiencyfamily
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This paper introduces EfficientNetV2, a new family of convolutional networks that have faster training speed and better parameter efficiency than previous models. To develop this family of models, we use a combination of training-aware neural architecture search and scaling, to jointly optimize training speed and parameter efficiency. The models were searched from the search space enriched with new ops such as Fused-MBConv. Our experiments show that EfficientNetV2 models train much faster than state-of-the-art models while being up to 6.8x smaller. Our training can be further sped up by progressively increasing the image size during training, but it often causes a drop in accuracy. To compensate for this accuracy drop, we propose to adaptively adjust regularization (e.g., dropout and data augmentation) as well, such that we can achieve both fast training and good accuracy. With progressive learning, our EfficientNetV2 significantly outperforms previous models on ImageNet and CIFAR/Cars/Flowers datasets. By pretraining on the same ImageNet21k, our EfficientNetV2 achieves 87.3% top-1 accuracy on ImageNet ILSVRC2012, outperforming the recent ViT by 2.0% accuracy while training 5x-11x faster using the same computing resources. Code will be available at https://github.com/google/automl/tree/master/efficientnetv2.

Discussion (0). Sign in to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 1,133 citations worldwide. Full citation record

  1. In-Context Learning for Wound Classification with Small Multimodal Language Models

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Retrieval-based in-context learning, not zero-shot prompting, drives wound-classification gains in small multimodal models, with Qwen 3.5 27B reaching 0.872 accuracy on Kaggle and 0.678 on Medetec.

  2. Scalable deep fusion of spaceborne lidar and synthetic aperture radar for global forest structural complexity mapping

    cs.CV 2025-10 conditional novelty 6.0 of 10

    A compact neural network fuses GEDI lidar with satellite radar to map forest structural complexity globally at 25 m resolution for 2015–2022, achieving R²=0.82 against held-out GEDI data.

  3. StixelNExT++: Lightweight Monocular Scene Segmentation and Representation for Collective Perception

    cs.CV 2025-07 conditional novelty 5.0 of 10

    A monocular neural network predicts 3D Stixels directly from RGB images in about 10 ms, with a self-defined Waymo evaluation showing competitive performance within 30 m.

  4. Exploring Budgeted Image Classification with Content-Sensitive Resource Allocation

    cs.AI 2026-07 conditional novelty 4.0 of 10

    A content-sensitive strategy that routes easy images to cheap decision points and hard images to expensive ones outperforms random allocation under a computational budget.

  5. Image Recognition with Vision and Language Embeddings of VLMs

    cs.CV 2025-09 conditional novelty 4.0 of 10

    A benchmark of dual-encoder VLMs finds text and image embeddings give complementary class accuracy, and a per-class precision fusion rule adds about 0.4% accuracy over either alone on ImageNet.

  6. Leveraging Pathology Foundation Models for Panoptic Segmentation of Melanoma in H&E Images

    eess.IV 2025-07 conditional novelty 4.0 of 10

    A network combining a pathology foundation model (Virchow2) with an Efficient-UNet segments melanoma tissue types and won the PUMA challenge tissue segmentation task.

  7. Chest Disease Detection In X-Ray Images Using Deep Learning Classification Method

    eess.IV 2025-05 conditional novelty 4.0 of 10

    Fine-tuned CNNs reach 96 to 98 percent test accuracy on a 57,111-image chest X-ray task, but Grad-CAM and the authors' own analysis show the models rely in part on non-lung artifacts.

  8. Automated Fetal Biometry Assessment with Deep Ensembles using Sparse-Sampling of 2D Intrapartum Ultrasound Images

    eess.IV 2025-05 reject novelty 3.0 of 10

    A fetal biometry pipeline using sparse sampling and deep ensembles reports high accuracy, but its published measurement errors conflict with its own results tables.

Pith tools