Pith. sign in

REVIEW 14 cited by

Swin Transformer V2: Scaling Up Capacity and Resolution

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 2111.09883 v2 pith:NKAVD4T6 submitted 2021-11-18 cs.CV

classification cs.CV
keywords trainingmodelsvisionimagesmethodresolutiontaskstimes
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
abstract

Large-scale NLP models have been shown to significantly improve the performance on language tasks with no signs of saturation. They also demonstrate amazing few-shot capabilities like that of human beings. This paper aims to explore large-scale models in computer vision. We tackle three major issues in training and application of large vision models, including training instability, resolution gaps between pre-training and fine-tuning, and hunger on labelled data. Three main techniques are proposed: 1) a residual-post-norm method combined with cosine attention to improve training stability; 2) A log-spaced continuous position bias method to effectively transfer models pre-trained using low-resolution images to downstream tasks with high-resolution inputs; 3) A self-supervised pre-training method, SimMIM, to reduce the needs of vast labeled images. Through these techniques, this paper successfully trained a 3 billion-parameter Swin Transformer V2 model, which is the largest dense vision model to date, and makes it capable of training with images of up to 1,536$\times$1,536 resolution. It set new performance records on 4 representative vision tasks, including ImageNet-V2 image classification, COCO object detection, ADE20K semantic segmentation, and Kinetics-400 video action classification. Also note our training is much more efficient than that in Google's billion-level visual models, which consumes 40 times less labelled data and 40 times less training time. Code is available at \url{https://github.com/microsoft/Swin-Transformer}.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 14 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Towards White-Box Deep Wireless Sensing

    cs.LG 2025-07 conditional novelty 6.0 of 10

    RF-CRATE derives a fully complex-valued white-box transformer for RF sensing from the sparse rate reduction principle and shows it matches black-box baselines across five datasets.

  2. Machine Learning from Explanations

    cs.LG 2025-07 conditional novelty 6.0 of 10

    A two-stage optimization pipeline that alternates label loss with a KL divergence between feature maps of masked and unmasked inputs improves accuracy and robustness in small-data classification.

  3. Mahalanobis++: Improving OOD Detection via Feature Normalization

    cs.LG 2025-05 conditional novelty 6.0 of 10

    L2-normalizing pre-logit features improves Mahalanobis-based out-of-distribution detection across 44 ImageNet models, reducing the average false positive rate by 7.6 percentage points.

  4. PEAR: Equal Area Weather Forecasting on the Sphere

    cs.LG 2025-05 conditional novelty 6.0 of 10

    A transformer weather model operating natively on the equal-area HEALPix grid beats an equiangular-grid counterpart at longer lead times with 2.6x fewer parameters.

  5. Beyond Pretty Pictures: Combined Single- and Multi-Image Super-resolution for Sentinel-2 Images

    eess.IV 2025-05 conditional novelty 5.0 of 10

    SEN4X, a hybrid single- and multi-image super-resolution network, lifts Sentinel-2 imagery to 2.5 m and improves land-cover classification accuracy in Hanoi over SISR, MISR, and stacked-input baselines.

  6. ORBIT-2: Scaling Exascale Vision Foundation Models for Weather and Climate Downscaling

    cs.LG 2025-05 conditional novelty 5.0 of 10

    A 10-billion-parameter climate downscaling model trained on 65,536 GPUs at up to 4.1 exaFLOPS, with R2 0.98 to 0.99 at 7 km, but with token-count and validation caveats.

  7. Geometry Matters: Benchmarking Scientific ML Approaches for Flow Prediction around Complex Geometries

    cs.LG 2024-12 conditional novelty 5.0 of 10

    On the FlowBench lid-driven cavity benchmark, vision-transformer foundation models outperform neural operators in data-limited regimes, but all models generalize poorly to out-of-range Reynolds numbers and geometry ge...

  8. Multi-Task Learning for Heterogeneous Prediction from Video Game State with Transfer Learning

    cs.LG 2026-07 conditional novelty 4.0 of 10

    On a large World of Tanks dataset, a shared multi-task model with equal weighting or PCGrad outperforms single-task models on average, and task/map pre-training helps most in low-data regimes.

  9. Transfer Learning and Mixup for Fine-Grained Few-Shot Fungi Classification

    cs.CV 2025-07 conditional novelty 4.0 of 10

    A transfer learning pipeline with feature-level mixup and weighted sampling outperformed competition baselines on few-shot fungi classification.

  10. Unified Local and Global Attention Interaction Modeling for Vision Transformers

    cs.CV 2024-12 conditional novelty 4.0 of 10

    Adding local and global token interactions before self-attention, via an aggressive convolution-pooling block and a concept-attention block, improves RetinaNet object detection mAP over non-pretrained ViT, Swin, and D...

  11. Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey

    cs.CL 2024-12 conditional novelty 4.0 of 10

    A comprehensive survey that frames multimodal understanding and generation as next token prediction and proposes a five-part taxonomy.

  12. Safety Monitoring of Machine Learning Perception Functions: a Survey

    cs.LG 2024-12 accept novelty 4.0 of 10

    A survey that organizes research on runtime safety monitors for ML perception into threat identification, requirements, detection, reaction, and evaluation, and lists open challenges.

  13. Survey on Question Answering over Visually Rich Documents: Methods, Challenges, and Trends

    cs.CL 2025-01 conditional novelty 3.0 of 10

    A structured overview of question answering over visually rich documents, comparing encoding, vision-only, and multi-page methods, and highlighting comparability issues in existing benchmarks.

  14. Combining physics-based and data-driven models: advancing the frontiers of research with Scientific Machine Learning

    math.NA 2025-01 conditional novelty 2.0 of 10

    A review that maps the field of Scientific Machine Learning and presents the authors' own cardiac simulation program as its flagship application.

Pith tools