ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learning

07/15/2020
by   Viktor Olsson, et al.
0

The state of the art in semantic segmentation is steadily increasing in performance, resulting in more precise and reliable segmentations in many different applications. However, progress is limited by the cost of generating labels for training, which sometimes requires hours of manual labor for a single image. Because of this, semi-supervised methods have been applied to this task, with varying degrees of success. A key challenge is that common augmentations used in semi-supervised classification are less effective for semantic segmentation. We propose a novel data augmentation mechanism called ClassMix, which generates augmentations by mixing unlabelled samples, by leveraging on the network's predictions for respecting object boundaries. We evaluate this augmentation technique on two common semi-supervised semantic segmentation benchmarks, showing that it attains state-of-the-art results. Lastly, we also provide extensive ablation studies comparing different design decisions and training regimes.

READ FULL TEXT

page 3

page 5

page 6

page 9

research
10/09/2021

Colour augmentation for improved semi-supervised semantic segmentation

Consistency regularization describes a class of approaches that have yie...
research
08/02/2021

Reliable Semantic Segmentation with Superpixel-Mix

Along with predictive performance and runtime speed, reliability is a ke...
research
01/25/2021

Mask-based Data Augmentation for Semi-supervised Semantic Segmentation

Semantic segmentation using convolutional neural networks (CNN) is a cru...
research
08/03/2022

Augmentation Learning for Semi-Supervised Classification

Recently, a number of new Semi-Supervised Learning methods have emerged....
research
10/31/2021

Smart(Sampling)Augment: Optimal and Efficient Data Augmentation for Semantic Segmentation

Data augmentation methods enrich datasets with augmented data to improve...
research
07/19/2023

Boundary-Refined Prototype Generation: A General End-to-End Paradigm for Semi-Supervised Semantic Segmentation

Prototype-based classification is a classical method in machine learning...
research
11/03/2021

HS3: Learning with Proper Task Complexity in Hierarchically Supervised Semantic Segmentation

While deeply supervised networks are common in recent literature, they t...

Please sign up or login with your details

Forgot password? Click here to reset