DeepAI AI Chat
Log In Sign Up

SemiCurv: Semi-Supervised Curvilinear Structure Segmentation

by   Xun Xu, et al.
Agency for Science, Technology and Research

Recent work on curvilinear structure segmentation has mostly focused on backbone network design and loss engineering. The challenge of collecting labelled data, an expensive and labor intensive process, has been overlooked. While labelled data is expensive to obtain, unlabelled data is often readily available. In this work, we propose SemiCurv, a semi-supervised learning (SSL) framework for curvilinear structure segmentation that is able to utilize such unlabelled data to reduce the labelling burden. Our framework addresses two key challenges in formulating curvilinear segmentation in a semi-supervised manner. First, to fully exploit the power of consistency based SSL, we introduce a geometric transformation as strong data augmentation and then align segmentation predictions via a differentiable inverse transformation to enable the computation of pixel-wise consistency. Second, the traditional mean square error (MSE) on unlabelled data is prone to collapsed predictions and this issue exacerbates with severe class imbalance (significantly more background pixels). We propose a N-pair consistency loss to avoid trivial predictions on unlabelled data. We evaluate SemiCurv on six curvilinear segmentation datasets, and find that with no more than 5 performance relative to its fully supervised counterpart.


page 1

page 3

page 5

page 6

page 11


Structured Consistency Loss for semi-supervised semantic segmentation

The consistency loss has played a key role in solving problems in recent...

More unlabelled data or label more data? A study on semi-supervised laparoscopic image segmentation

Improving a semi-supervised image segmentation task has the option of ad...

OffRoadTranSeg: Semi-Supervised Segmentation using Transformers on OffRoad environments

We present OffRoadTranSeg, the first end-to-end framework for semi-super...

Active Regression with Adaptive Huber Loss

This paper addresses the scalar regression problem through a novel solut...

Unbiased Subclass Regularization for Semi-Supervised Semantic Segmentation

Semi-supervised semantic segmentation learns from small amounts of label...

Learning Morphological Feature Perturbations for Calibrated Semi-Supervised Segmentation

We propose MisMatch, a novel consistency-driven semi-supervised segmenta...

Panoptic One-Click Segmentation: Applied to Agricultural Data

In weed control, precision agriculture can help to greatly reduce the us...

Code Repositories