Region-of-interest guided Supervoxel Inpainting for Self-supervision

06/26/2020
by   Subhradeep Kayal, et al.
0

Self-supervised learning has proven to be invaluable in making best use of all of the available data in biomedical image segmentation. One particularly simple and effective mechanism to achieve self-supervision is inpainting, the task of predicting arbitrary missing areas based on the rest of an image. In this work, we focus on image inpainting as the self-supervised proxy task, and propose two novel structural changes to further enhance the performance of a deep neural network. We guide the process of generating images to inpaint by using supervoxel-based masking instead of random masking, and also by focusing on the area to be segmented in the primary task, which we term as the region-of-interest. We postulate that these additions force the network to learn semantics that are more attuned to the primary task, and test our hypotheses on two applications: brain tumour and white matter hyperintensities segmentation. We empirically show that our proposed approach consistently outperforms both supervised CNNs, without any self-supervision, and conventional inpainting-based self-supervision methods on both large and small training set sizes.

READ FULL TEXT
research
11/25/2022

WSSL: Weighted Self-supervised Learning Framework For Image-inpainting

Image inpainting is the process of regenerating lost parts of the image....
research
02/28/2020

Instance Separation Emerges from Inpainting

Deep neural networks trained to inpaint partially occluded images show a...
research
06/26/2021

In-N-Out: Towards Good Initialization for Inpainting and Outpainting

In computer vision, recovering spatial information by filling in masked ...
research
07/05/2023

Source Identification: A Self-Supervision Task for Dense Prediction

The paradigm of self-supervision focuses on representation learning from...
research
02/21/2022

Self-Supervised Bulk Motion Artifact Removal in Optical Coherence Tomography Angiography

Optical coherence tomography angiography (OCTA) is an important imaging ...
research
03/10/2023

Self-Supervised CSF Inpainting with Synthetic Atrophy for Improved Accuracy Validation of Cortical Surface Analyses

Accuracy validation of cortical thickness measurement is a difficult pro...
research
05/22/2022

Self-supervised U-net for few-shot learning of object segmentation in microscopy images

State-of-the-art segmentation performances are achieved by deep neural n...

Please sign up or login with your details

Forgot password? Click here to reset