Skip to content

Calibrate to Interpret

Trustworthy machine learning is driving a large number of ML community works in order to improve ML acceptance and adoption. The main aspect of trustworthy machine learning are the followings: fairness, uncertainty, robustness, explainability and formal guaranties. Each of these individual domains gains the ML community interest, visible by the number of related publications. However, few works tackle the interconnection between these fields. In this paper, we show a first link between uncertainty and explainability, by studying the relation between calibration and interpretation. As the calibration of a given model changes the way it scores samples, and interpretation approaches often rely on these scores, it seems safe to assume that the confidence-calibration of a model interacts with our ability to interpret such model. In this paper, we show, in the context of networks trained on image classification tasks, to what extent interpretations are sensitive to confidence-calibration. It leads us to suggest a simple practice to improve the interpretation outcomes : Calibrate to Interpret.

Gregory Scafarto, Nicolas Posocco, Antoine Bonnefoy, Calibrate to Interpret, In Proc. of The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2022), September 2022.

Click here to access the paper.

Releated Posts

Insights from GTC Paris 2025

Among the NVIDIA GTC Paris crowd was our CTO Sabri Skhiri, and from quantum computing breakthroughs to the full-stack AI advancements powering industrial digital twins and robotics, there is a lot to share! Explore with Sabri GTC 2025 trends, keynotes, and what it means for businesses looking to innovate.
Read More

Development & Evaluation of Automated Tumour Monitoring by Image Registration Based on 3D (PET/CT) Images

Tumor tracking in PET/CT is essential for monitoring cancer progression and guiding treatment strategies. Traditionally, nuclear physicians manually track tumors, focusing on the five largest ones (PERCIST criteria), which is both time-consuming and imprecise. Automated tumor tracking can allow matching of the numerous metastatic lesions across scans, enhancing tumor change monitoring.
Read More