English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Machine Learning (ML) is a fundamental part of modern perception systems. Inthe last decade, the performance of computer vision using trained deep neuralnetworks has outperformed previous approaches based on careful featureengineering. However, the opaqueness of large ML models is a substantialimpediment for critical applications such as in the automotive context. As aremedy, Gradient-weighted Class Activation Mapping (Grad-CAM) has been proposedto provide visual explanations of model internals. In this paper, wedemonstrate how Grad-CAM heatmaps can be used to increase the explainability ofan image recognition model trained for a pedestrian underpass. We argue how theheatmaps support compliance to the EU's seven key requirements for TrustworthyAI. Finally, we propose adding automated heatmap analysis as a pipe segment inan MLOps pipeline. We believe that such a building block can be used toautomatically detect if a trained ML-model is activated based on invalid pixelsin test images, suggesting biased models.

Test Automation with Grad-CAM Heatmaps -- A Future Pipe Segment in MLOps for Vision AI?