Universal Semi-Supervised Semantic Segmentation

by   Tarun Kalluri, et al.

In recent years, the need for semantic segmentation has arisen across several different applications and environments. However, the expense and redundancy of annotation often limits the quantity of labels available for training in any domain, while deployment is easier if a single model works well across domains. In this paper, we pose the novel problem of universal semi-supervised semantic segmentation and propose a solution framework, to meet the dual needs of lower annotation and deployment costs. In contrast to counterpoints such as fine tuning, joint training or unsupervised domain adaptation, universal semi-supervised segmentation ensures that across all domains: (i) a single model is deployed, (ii) unlabeled data is used, (iii) performance is improved, (iv) only a few labels are needed and (v) label spaces may differ. To address this, we minimize supervised as well as within and cross-domain unsupervised losses, introducing a novel feature alignment objective based on pixel-aware entropy regularization for the latter. We demonstrate quantitative advantages over other approaches on several combinations of segmentation datasets across different geographies (Germany, England, India) and environments (outdoors, indoors), as well as qualitative insights on the aligned representations.


page 1

page 3

page 8

page 12


Semi-supervised Domain Adaptation for Semantic Segmentation

Deep learning approaches for semantic segmentation rely primarily on sup...

Domain Adaptation for Semantic Segmentation via Patch-Wise Contrastive Learning

We introduce a novel approach to unsupervised and semi-supervised domain...

Semi-supervised Domain Adaptation based on Dual-level Domain Mixing for Semantic Segmentation

Data-driven based approaches, in spite of great success in many tasks, h...

Semi-Supervised Learning for Visual Bird's Eye View Semantic Segmentation

Visual bird's eye view (BEV) semantic segmentation helps autonomous vehi...

Mixed-domain Training Improves Multi-Mission Terrain Segmentation

Planetary rover missions must utilize machine learning-based perception ...

Learning Semantic Segmentation from Multiple Datasets with Label Shifts

With increasing applications of semantic segmentation, numerous datasets...

AnyLoc: Towards Universal Visual Place Recognition

Visual Place Recognition (VPR) is vital for robot localization. To date,...

Please sign up or login with your details

Forgot password? Click here to reset