Magnifying Networks for Images with Billions of Pixels

12/12/2021
by   Neofytos Dimitriou, et al.
17

The shift towards end-to-end deep learning has brought unprecedented advances in many areas of computer vision. However, there are cases where the input images are excessively large, deeming end-to-end approaches impossible. In this paper, we introduce a new network, the Magnifying Network (MagNet), which can be trained end-to-end independently of the input image size. MagNets combine convolutional neural networks with differentiable spatial transformers, in a new way, to navigate and successfully learn from images with billions of pixels. Drawing inspiration from the magnifying nature of an ordinary brightfield microscope, a MagNet processes a downsampled version of an image, and without supervision learns how to identify areas that may carry value to the task at hand, upsamples them, and recursively repeats this process on each of the extracted patches. Our results on the publicly available Camelyon16 and Camelyon17 datasets first corroborate to the effectiveness of MagNets and the proposed optimization framework and second, demonstrate the advantage of Magnets' built-in transparency, an attribute of utmost importance for critical processes such as medical diagnosis.

READ FULL TEXT

page 1

page 5

page 6

page 7

research
11/11/2019

Streaming convolutional neural networks for end-to-end learning with multi-megapixel images

Due to memory constraints on current hardware, most convolution neural n...
research
10/25/2022

Learning Explicit Object-Centric Representations with Vision Transformers

With the recent successful adaptation of transformers to the vision doma...
research
10/16/2018

ReDMark: Framework for Residual Diffusion Watermarking on Deep Networks

Due to the rapid growth of machine learning tools and specifically deep ...
research
03/30/2021

Differentiable Drawing and Sketching

We present a bottom-up differentiable relaxation of the process of drawi...
research
03/19/2021

Cluster-to-Conquer: A Framework for End-to-End Multi-Instance Learning for Whole Slide Image Classification

In recent years, the availability of digitized Whole Slide Images (WSIs)...
research
06/30/2017

A selectional auto-encoder approach for document image binarization

Binarization plays a key role in the automatic information retrieval fro...

Please sign up or login with your details

Forgot password? Click here to reset