5 papers
Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More
Feng Wang, Yaodong Yu, Guoyizhe Wei +4
Since the introduction of Vision Transformer (ViT), patchification has long been regarded as a de facto image tokenization approach for plain visual architectures. By compressing t…
Fast-DDPM: Fast Denoising Diffusion Probabilistic Models for Medical Image-to-Image Generation
Hongxu Jiang, Muhammad Imran, Teng Zhang +4
Denoising diffusion probabilistic models (DDPMs) have achieved unprecedented success in computer vision. However, they remain underutilized in medical imaging, a field crucial for…
Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency
Feng Wang, Timing Yang, Yaodong Yu +7
In this work, we introduce the Adventurer series models where we treat images as sequences of patch tokens and employ uni-directional language models to learn visual representation…
Mamba-R: Vision Mamba ALSO Needs Registers
Feng Wang, Jiahao Wang, Sucheng Ren +6
Similar to Vision Transformers, this paper identifies artifacts also present within the feature maps of Vision Mamba. These artifacts, corresponding to high-norm tokens emerging in…
Multi-Class Segmentation of Aortic Branches and Zones in Computed Tomography Angiography: The AortaSeg24 Challenge
Muhammad Imran, Jonathan R. Krebs, Vishal Balaji Sivaraman +60
Multi-class segmentation of the aorta in computed tomography angiography (CTA) scans is essential for diagnosing and planning complex endovascular treatments for patients with aort…