Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bank

This work presents a novel approach for semi-supervised semantic segmentation. The key element of this approach is our contrastive learning module that enforces the segmentation network to yield similar pixel-level feature representations for same-class samples across the whole dataset. To achieve t...

Full description

Saved in:
Bibliographic Details
Main Authors: Alonso, Inigo, Sabater, Alberto, Ferstl, David, Montesano, Luis, Murillo, Ana C.
Format: Conference Proceeding
Language:English
Subjects:
Benchmark testing
Codes
Computer vision
Scene analysis and understanding
Semantics
Task analysis
Training
Transfer/Low-shot/Semi/Unsupervised Learning
Vision for robotics and autonomous vehicles
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This work presents a novel approach for semi-supervised semantic segmentation. The key element of this approach is our contrastive learning module that enforces the segmentation network to yield similar pixel-level feature representations for same-class samples across the whole dataset. To achieve this, we maintain a memory bank which is continuously updated with relevant and high-quality feature vectors from labeled data. In an end-to-end training, the features from both labeled and unlabeled data are optimized to be similar to same-class samples from the memory bank. Our approach not only outperforms the current state-of-the-art for semi-supervised semantic segmentation but also for semi-supervised domain adaptation on well-known public benchmarks, with larger improvements on the most challenging scenarios, i.e., less available labeled data. Code is available at https://github.com/Shathe/SemiSeg-Contrastive
ISSN:2380-7504
DOI:10.1109/ICCV48922.2021.00811