Search Results for author:
Found 8 papers, 3 papers with code
Aggregation Model Hyperparameters Matter in Digital Pathology
Digital pathology has significantly advanced disease detection and pathologist efficiency through the analysis of gigapixel whole-slide images (WSI).
Explicitly Minimizing the Blur Error of Variational Autoencoders
Variational autoencoders (VAEs) are powerful generative modelling methods, however they suffer from blurry generated samples and reconstructions compared to the images they have been trained on.
Unsupervised Superpixel Generation using Edge-Sparse Embedding
Partitioning an image into superpixels based on the similarity of pixels with respect to features such as colour or spatial location can significantly reduce data complexity and improve subsequent image processing tasks.
Wiener Guided DIP for Unsupervised Blind Image Deconvolution
In addition, the image generator reproduces low-frequency features of the deconvolved image faster than that of a blurry image.
ISNAS-DIP: Image-Specific Neural Architecture Search for Deep Image Prior
Our experiments show that image-specific metrics can reduce the search space to a small cohort of models, of which the best model outperforms current NAS approaches for image restoration.
Quality-Aware Memory Network for Interactive Volumetric Image Segmentation
The proposed network has two appealing characteristics: 1) The memory-augmented network offers the ability to quickly encode past segmentation information, which will be retrieved for the segmentation of other slices; 2) The quality assessment module enables the model to directly estimate the qualities of segmentation predictions, which allows an active learning paradigm where users preferentially label the lowest-quality slice for multi-round refinement.
Gradient flow encoding with distance optimization adaptive step size
In this work, we investigate a decoder-only method that uses gradient flow to encode data samples in the latent space.
Iterative Interaction Training for Segmentation Editing Networks
Automatic segmentation has great potential to facilitate morphological measurements while simultaneously increasing efficiency.
