Skip to main content
Search

# Swin Transformer

5 related articles

Subscribe to updates
  1. arXiv

    PoreTimeNet segments a whole micro-CT sequence at once, cutting carbonate porosity error from 0.97 to 0.28 points

    A single time-resolved micro-CT experiment can yield tens to hundreds of three-dimensional images, and segmenting each one independently lets errors drift between frames and be mistaken for physical change. PoreTimeNet feeds several images from one temporal window through a shared spatial encoder and borrows information across time steps with temporal attention and decoder fusion. On a carbonate dissolution sequence its mean absolute porosity error was 0.28 percentage points against 0.97 for a 3D model that ignores temporal information, and rock boundary F1 rose from 0.833 to 0.941.

  2. CWAI folds pollutants and weather into one learned state, beating WRF-Chem error at 10 days across six pollutants

    Regional air-quality forecasting has relied on online-coupled numerical chemistry-weather models whose skill is sensitive to meteorological initial conditions, emission inventories and lateral boundary conditions. CWAI treats meteorology, particles and reactive gases as one joint atmospheric state, driven by two consecutive states, emissions and static surface descriptors through a hierarchical Swin Transformer, and rolls out 40 six-hour steps to a 10-day forecast. Against WRF-Chem over 62 January and July 2020 starts, CWAI had lower initialization-weighted RMSE for all six surface pollutants, from 15.8% for PM2.5 to 25.8% for NO2.

  3. arXiv

    One2N pushes a 0.7° forecast model to 0.07°: four weeks on one 80 GB GPU, tropospheric skill intact

    As Earth-system AI models approach kilometre scales, halving grid spacing quadruples the grid-point count and the end-to-end training cost. One2N splits resolution refinement into successive increments: at each level the complete parent predictor is frozen and only a cross-resolution residual correction module is trained, so the parent's activations and optimizer states are never retained. One refinement level on the NeuralGCM-0.7° baseline yields One2N-0.07°, trained for about four weeks on a single 80 GB A800 GPU; against HRES-0.07° analyses it keeps the parent's tropospheric skill while reducing upper-stratospheric errors and resolving finer structure.

  4. When hair breaks a lesion border, repair the high frequencies before decoding: 89.69% Dice on ISIC 2018

    In dermoscopic images, hair occlusion, uneven illumination and weak local contrast fragment lesion boundaries, while self-attention tends to emphasize lower-frequency content and leaves those weak borders underrepresented in skip connections. Swin-WaveNet decomposes each encoder skip feature with a wavelet transform, applies selective state-space scanning only to the high-frequency subbands to reconnect interrupted contours, gates shallow high-frequency responses with deeper semantic guidance to suppress hair and artifact structures, and sharpens boundaries during upsampling with high-frequency attention. On ISIC 2018 it reached a mean Dice of 89.69% and HD95 of 23.60 pixels over three runs, close to Swin-Unet, and 91.69% Dice on ISIC 2017 without fine-tuning.

  5. bioRxiv

    RSAUNet: A Hybrid Residual–Swin Transformer Design with Attention for Prostate Cancer Segmentation

    The study proposes RSAUNet, a deep learning architecture that combines residual convolutional blocks, Swin Transformer blocks, and attention mechanisms inside a U-Net backbone for MRI prostate cancer segmentation, reporting a Dice coefficient of 0.998 and a Jaccard index (IoU) of 0.965 on a public Kaggle prostate annotation dataset, together with an ablation study tracking loss, accuracy, Dice, and mean IoU as each component is added.

You’re all caught up