Pixel Contrastive-Consistent Semi-Supervised Semantic Segmentation

08/20/2021
by   Yuanyi Zhong, et al.
0

We present a novel semi-supervised semantic segmentation method which jointly achieves two desiderata of segmentation model regularities: the label-space consistency property between image augmentations and the feature-space contrastive property among different pixels. We leverage the pixel-level L2 loss and the pixel contrastive loss for the two purposes respectively. To address the computational efficiency issue and the false negative noise issue involved in the pixel contrastive loss, we further introduce and investigate several negative sampling techniques. Extensive experiments demonstrate the state-of-the-art performance of our method (PC2Seg) with the DeepLab-v3+ architecture, in several challenging semi-supervised settings derived from the VOC, Cityscapes, and COCO datasets.

READ FULL TEXT

page 1

page 11

page 12

research
04/28/2022

Region-level Contrastive and Consistency Learning for Semi-Supervised Semantic Segmentation

Current semi-supervised semantic segmentation methods mainly focus on de...
research
06/03/2021

Attention-Guided Supervised Contrastive Learning for Semantic Segmentation

Contrastive learning has shown superior performance in embedding global ...
research
10/26/2022

Boosting Semi-Supervised Semantic Segmentation with Probabilistic Representations

Recent breakthroughs in semi-supervised semantic segmentation have been ...
research
09/25/2021

Contrastive Learning for Mitochondria Segmentation

Mitochondria segmentation in electron microscopy images is essential in ...
research
04/09/2021

Bootstrapping Semantic Segmentation with Regional Contrast

We present ReCo, a contrastive learning framework designed at a regional...
research
11/12/2019

Negative sampling in semi-supervised learning

We introduce Negative Sampling in Semi-Supervised Learning (NS3L), a sim...
research
04/13/2021

Probing Negative Sampling Strategies to Learn GraphRepresentations via Unsupervised Contrastive Learning

Graph representation learning has long been an important yet challenging...

Please sign up or login with your details

Forgot password? Click here to reset