Pseudo-Label Noise Suppression Techniques for Semi-Supervised Semantic Segmentation

10/19/2022
by   Sebastian Scherer, et al.
0

Semi-supervised learning (SSL) can reduce the need for large labelled datasets by incorporating unlabelled data into the training. This is particularly interesting for semantic segmentation, where labelling data is very costly and time-consuming. Current SSL approaches use an initially supervised trained model to generate predictions for unlabelled images, called pseudo-labels, which are subsequently used for training a new model from scratch. Since the predictions usually do not come from an error-free neural network, they are naturally full of errors. However, training with partially incorrect labels often reduce the final model performance. Thus, it is crucial to manage errors/noise of pseudo-labels wisely. In this work, we use three mechanisms to control pseudo-label noise and errors: (1) We construct a solid base framework by mixing images with cow-patterns on unlabelled images to reduce the negative impact of wrong pseudo-labels. Nevertheless, wrong pseudo-labels still have a negative impact on the performance. Therefore, (2) we propose a simple and effective loss weighting scheme for pseudo-labels defined by the feedback of the model trained on these pseudo-labels. This allows us to soft-weight the pseudo-label training examples based on their determined confidence score during training. (3) We also study the common practice to ignore pseudo-labels with low confidence and empirically analyse the influence and effect of pseudo-labels with different confidence ranges on SSL and the contribution of pseudo-label filtering to the achievable performance gains. We show that our method performs superior to state of-the-art alternatives on various datasets. Furthermore, we show that our findings also transfer to other tasks such as human pose estimation. Our code is available at https://github.com/ChristmasFan/SSL_Denoising_Segmentation.

READ FULL TEXT

page 1

page 4

page 7

page 10

research
01/11/2023

Co-training with High-Confidence Pseudo Labels for Semi-supervised Medical Image Segmentation

High-quality pseudo labels are essential for semi-supervised semantic se...
research
02/11/2022

Predicting Out-of-Distribution Error with the Projection Norm

We propose a metric – Projection Norm – to predict a model's performance...
research
04/05/2022

Semi-supervised Semantic Segmentation with Error Localization Network

This paper studies semi-supervised learning of semantic segmentation, wh...
research
03/08/2023

Semi-Supervised 2D Human Pose Estimation Driven by Position Inconsistency Pseudo Label Correction Module

In this paper, we delve into semi-supervised 2D human pose estimation. T...
research
08/27/2020

Webly Supervised Image Classification with Self-Contained Confidence

This paper focuses on webly supervised learning (WSL), where datasets ar...
research
04/23/2023

Semi-Supervised Semantic Segmentation With Region Relevance

Semi-supervised semantic segmentation aims to learn from a small amount ...
research
08/18/2023

Inferior Alveolar Nerve Segmentation in CBCT images using Connectivity-Based Selective Re-training

Inferior Alveolar Nerve (IAN) canal detection in CBCT is an important st...

Please sign up or login with your details

Forgot password? Click here to reset