Deep is a Luxury We Don't Have


Ahmed Taha*      Yen Nhi Truong Vu*      Brent Mombourquette      Thomas Matthews      Jason Su      Sadanand Singh


arXiv    Github    Poster


Medical images come in high resolutions. A high resolution is vital for finding malignant tissues at an early stage. Yet, this resolution presents a challenge in terms of modeling long range dependencies. Shallow transformers eliminate this problem, but they suffer from quadratic complexity. In this paper, we tackle this complexity by leveraging a linear self-attention approximation. Through this approximation, we propose an efficient vision model called HCT that stands for High resolution Convolutional Transformer. HCT brings transformers' merits to high resolution images at a significantly lower cost. We evaluate HCT using a high resolution mammography dataset. HCT is significantly superior to its CNN counterpart. Furthermore, we demonstrate HCT's fitness for medical images by evaluating its effective receptive field.


  title={Deep is a Luxury We Don't Have},
  author={Taha, Ahmed and Truong Vu, Yen Nhi and Mombourquette, Brent and Matthews, Thomas Paul and Su, Jason and Singh, Sadanand},
  booktitle={International Conference on Medical Image Computing and Computer-Assisted Intervention},