We propose DPCrossU-Net, a dual-branch parallel encoder that integrates multi-scale convolutional and Transformer-based representations. Parallel CNN and ViT branches are employed to capture ...
AI-Driven-Ultrasound-Smart-Gain-Physics-Informed-Auto-TGC-Object-Segmentation An AI-driven "Zero-Button" ultrasound image enhancement pipeline that combines sound wave physics with a PyTorch U-Net to ...
Robust Auto-associative Memory via Convolutional Restricted Hopfield Networks Ci Lin, Tet Yeap, Iluju Kiringa PolicyGuard: Towards Test-time and Step-level Adversary (Backdoor) Defense for ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results