DeepAI AI Chat
Log In Sign Up

Dense FixMatch: a simple semi-supervised learning method for pixel-wise prediction tasks

by   Miquel Martí i Rabadán, et al.
KTH Royal Institute of Technology

We propose Dense FixMatch, a simple method for online semi-supervised learning of dense and structured prediction tasks combining pseudo-labeling and consistency regularization via strong data augmentation. We enable the application of FixMatch in semi-supervised learning problems beyond image classification by adding a matching operation on the pseudo-labels. This allows us to still use the full strength of data augmentation pipelines, including geometric transformations. We evaluate it on semi-supervised semantic segmentation on Cityscapes and Pascal VOC with different percentages of labeled data and ablate design choices and hyper-parameters. Dense FixMatch significantly improves results compared to supervised learning using only labeled data, approaching its performance with 1/4 of the labeled samples.


Semi-supervised Learning with Robust Loss in Brain Segmentation

In this work, we used a semi-supervised learning method to train deep le...

Semi-Supervised Semantic Segmentation with High- and Low-level Consistency

The ability to understand visual information from limited labeled data i...

Semi-supervised learning by selective training with pseudo labels via confidence estimation

We propose a novel semi-supervised learning (SSL) method that adopts sel...

Swapping Semantic Contents for Mixing Images

Deep architecture have proven capable of solving many tasks provided a s...

Density Fixing: Simple yet Effective Regularization Method based on the Class Prior

Machine learning models suffer from overfitting, which is caused by a la...

A Probabilistic Framework for Discriminative and Neuro-Symbolic Semi-Supervised Learning

In semi-supervised learning (SSL), a rule to predict labels y for data x...

SemiCurv: Semi-Supervised Curvilinear Structure Segmentation

Recent work on curvilinear structure segmentation has mostly focused on ...