Wau Labs
Menu
Insights

Notes from the work.

Published research and technical perspectives on building AI that works outside the demonstration.

Research

Published work.

Semantic segmentation map of an urban street scene
ISPACS 2022

TransUNet for Cross-Domain Semantic Segmentation of Urban Scenery

Applying a transformer–CNN architecture to urban scenery, and studying how simulated images can complement real-world training data.

Dew-covered spider web, the original publication’s accompanying photograph
ISPACS 2022 · Demo paper

Liveness Detection for Images and Audio

An overview of visual and audio liveness detection, with implementation details including convolutional neural networks and Mel spectrograms for audio.

Coloured edge-map representation of an oil-palm bunch
BMVC 2021

Coloured Edge Maps for Oil Palm Ripeness Classification

Investigating coloured edge maps as CNN inputs for oil-palm ripeness grading, with a focus on robustness to changes in lighting.

Our editorial focus

The questions behind useful AI.

From model to field

What changes when vision systems meet real operating conditions.

Beyond the chatbot

How analytical agents fit into technical and business workflows.

Testing feasibility

How to investigate whether a bespoke AI problem is tractable.

Our project summaries offer a first look at the work behind these topics.

Explore our projects