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

by   Junhao Dong, et al.

Prototype-based classification is a classical method in machine learning, and recently it has achieved remarkable success in semi-supervised semantic segmentation. However, the current approach isolates the prototype initialization process from the main training framework, which appears to be unnecessary. Furthermore, while the direct use of K-Means algorithm for prototype generation has considered rich intra-class variance, it may not be the optimal solution for the classification task. To tackle these problems, we propose a novel boundary-refined prototype generation (BRPG) method, which is incorporated into the whole training framework. Specifically, our approach samples and clusters high- and low-confidence features separately based on a confidence threshold, aiming to generate prototypes closer to the class boundaries. Moreover, an adaptive prototype optimization strategy is introduced to make prototype augmentation for categories with scattered feature distributions. Extensive experiments on the PASCAL VOC 2012 and Cityscapes datasets demonstrate the superiority and scalability of the proposed method, outperforming the current state-of-the-art approaches. The code is available at xxxxxxxxxxxxxx.


page 8

page 14

page 41

page 42


Semi-supervised Semantic Segmentation with Prototype-based Consistency Regularization

Semi-supervised semantic segmentation requires the model to effectively ...

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

The state of the art in semantic segmentation is steadily increasing in ...

Number-Adaptive Prototype Learning for 3D Point Cloud Semantic Segmentation

3D point cloud semantic segmentation is one of the fundamental tasks for...

Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigation

While self-training has advanced semi-supervised semantic segmentation, ...

A differentiable Gaussian Prototype Layer for explainable Segmentation

We introduce a Gaussian Prototype Layer for gradient-based prototype lea...

Learning a Discriminative Feature Network for Semantic Segmentation

Most existing methods of semantic segmentation still suffer from two asp...

Please sign up or login with your details

Forgot password? Click here to reset