A Three-Stage Self-Training Framework for Semi-Supervised Semantic Segmentation

12/01/2020
by   Rihuan Ke, et al.
0

Semantic segmentation has been widely investigated in the community, in which the state of the art techniques are based on supervised models. Those models have reported unprecedented performance at the cost of requiring a large set of high quality segmentation masks. To obtain such annotations is highly expensive and time consuming, in particular, in semantic segmentation where pixel-level annotations are required. In this work, we address this problem by proposing a holistic solution framed as a three-stage self-training framework for semi-supervised semantic segmentation. The key idea of our technique is the extraction of the pseudo-masks statistical information to decrease uncertainty in the predicted probability whilst enforcing segmentation consistency in a multi-task fashion. We achieve this through a three-stage solution. Firstly, we train a segmentation network to produce rough pseudo-masks which predicted probability is highly uncertain. Secondly, we then decrease the uncertainty of the pseudo-masks using a multi-task model that enforces consistency whilst exploiting the rich statistical information of the data. We compare our approach with existing methods for semi-supervised semantic segmentation and demonstrate its state-of-the-art performance with extensive experiments.

READ FULL TEXT

page 3

page 7

research
12/06/2021

Semantic Segmentation In-the-Wild Without Seeing Any Segmentation Examples

Semantic segmentation is a key computer vision task that has been active...
research
08/31/2023

Domain Adaptive Synapse Detection with Weak Point Annotations

The development of learning-based methods has greatly improved the detec...
research
12/14/2021

n-CPS: Generalising Cross Pseudo Supervision to n networks for Semi-Supervised Semantic Segmentation

We present n-CPS - a generalisation of the recent state-of-the-art cross...
research
02/19/2021

Scribble-Supervised Semantic Segmentation by Uncertainty Reduction on Neural Representation and Self-Supervision on Neural Eigenspace

Scribble-supervised semantic segmentation has gained much attention rece...
research
03/02/2023

Conflict-Based Cross-View Consistency for Semi-Supervised Semantic Segmentation

Semi-supervised semantic segmentation has recently gained increasing res...
research
06/27/2021

Semi-supervised Semantic Segmentation with Directional Context-aware Consistency

Semantic segmentation has made tremendous progress in recent years. Howe...
research
06/24/2023

Semantic Segmentation of Porosity in 4D Spatio-Temporal X-ray μCT of Titanium Coated Ni wires using Deep Learning

A fully convolutional neural network was used to measure the evolution o...

Please sign up or login with your details

Forgot password? Click here to reset