Label-efficient learning

Reef Scene Understanding

Expert annotation of underwater imagery is slow and expensive. We develop methods that learn from very sparse labels.

Why it matters

Coral reef surveys produce far more images than experts can label. Our point-label-aware superpixels and human-in-the-loop methods turn 5 to 25 labelled points per image into dense segmentation, and image-level labels alone are enough for coarse seagrass mapping. We have also surveyed label-efficient underwater scene understanding and shown how strongly domain and species affect object detection performance.

Team

Members of my group at the QUT Centre for Robotics and close collaborators.

Tobias Fischer Tobias Fischer
Lead
Scarlett Raine Scarlett Raine
Collaborator
Melanie Wille Melanie Wille
PhD student
Dorian Tsai
Collaborator
Matthew Dunbabin
Collaborator

Publications

Selected papers from this line of work. See all publications.

WACV 2027

Why Domain Matters: Domain-Aware Benchmarking of Underwater Object Detection and Annotation Quality

Melanie Wille, Dimity Miller, Tobias Fischer, and Scarlett Raine

IEEE/CVF Winter Conference on Applications of Computer Vision 2027

WACV 2026

Are All Marine Species Created Equal? Performance Disparities in Underwater Object Detection

Melanie Wille, Tobias Fischer, and Scarlett Raine

IEEE/CVF Winter Conference on Applications of Computer Vision 2026

AAAI 2026

AI-Driven Marine Robotics: Emerging Trends in Underwater Perception and Ecosystem Monitoring

Scarlett Raine and Tobias Fischer

Annual AAAI Conference on Artificial Intelligence (Emerging Trends in AI Track) 2026

JOE 2026

Human-in-the-Loop Segmentation of Multi-species Coral Imagery

Scarlett Raine, Ross Marchant, Brano Kusy, Frederic Maire, Niko Suenderhauf, and Tobias Fischer

IEEE Journal of Oceanic Engineering 2026

arXiv 2024

Reducing Label Dependency for Underwater Scene Understanding: A Survey of Datasets, Techniques and Applications

Scarlett Raine, Frederic Maire, Niko Suenderhauf, and Tobias Fischer

arXiv 2411.11287

WACV 2024

Image Labels Are All You Need for Coarse Seagrass Segmentation

Scarlett Raine, Ross Marchant, Brano Kusy, Frederic Maire, and Tobias Fischer

IEEE/CVF Winter Conference on Applications of Computer Vision 2024

RAL 2022 + IROS 2022

Point Label Aware Superpixels for Multi-species Segmentation of Underwater Imagery

Scarlett Raine, Ross Marchant, Brano Kusy, Frederic Maire, and Tobias Fischer

IEEE Robotics and Automation Letters 2022 · Also selected for presentation at IROS 2022