Search Results for author:
Found 3 papers, 0 papers with code
Swin-Free: Achieving Better Cross-Window Attention and Efficiency with Size-varying Window
To mitigate this issue, we propose Swin-Free in which we apply size-varying windows across stages, instead of shifting windows, to achieve cross-connection among local windows.
Depth Estimation with Simplified Transformer
Transformer and its variants have shown state-of-the-art results in many vision tasks recently, ranging from image classification to dense prediction.
HAWKEYE: Adversarial Example Detector for Deep Neural Networks
Adversarial examples (AEs) are images that can mislead deep neural network (DNN) classifiers via introducing slight perturbations into original images.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
