Resolution Invariant Autoencoder
This addresses a domain-specific problem in medical imaging analysis by providing a unified approach to handle resolution variations, though it is incremental as it builds on existing autoencoder methods.
The paper tackles the challenge of varying image resolutions in medical imaging by introducing a resolution-invariant autoencoder that adapts spatial resizing at each layer, enabling consistent latent space resolution and outperforming baselines in tasks like super-resolution and classification with minimal performance loss.
Deep learning has significantly advanced medical imaging analysis, yet variations in image resolution remain an overlooked challenge. Most methods address this by resampling images, leading to either information loss or computational inefficiencies. While solutions exist for specific tasks, no unified approach has been proposed. We introduce a resolution-invariant autoencoder that adapts spatial resizing at each layer in the network via a learned variable resizing process, replacing fixed spatial down/upsampling at the traditional factor of 2. This ensures a consistent latent space resolution, regardless of input or output resolution. Our model enables various downstream tasks to be performed on an image latent whilst maintaining performance across different resolutions, overcoming the shortfalls of traditional methods. We demonstrate its effectiveness in uncertainty-aware super-resolution, classification, and generative modelling tasks and show how our method outperforms conventional baselines with minimal performance loss across resolutions.