Publications by Dotphoton team

While there are methods to prospectively validate the robustness of machine learning models to such dataset drifts, existing approaches do not account for explicit models of machine learning’s primary object of interest: the data. This limits our ability to study and understand the relationship between data generation and downstream machine learning model performance in a physically accurate manner. In this study, we demonstrate how to overcome this limitation by pairing traditional machine learning with physical optics to obtain explicit and differentiable data models.

This report by the Focus Group on Artificial Intelligence for Health (FG-AI4H) goal is to assist in understanding the expectations of the regulatory bodies, promote the step-by-step implementation of the safety and effectiveness of AI/ML-based software-as-medical devices, and fill the current gap in international AI/ML-based medical device standards to the greatest extent possible.

Once the raw data is collected, it is processed through a complex image signal processing (ISP) pipeline to produce an image compatible with human perception. However, this processing is rarely considered in machine learning modelling because available benchmark data sets are generally not in raw format. This study shows how to embed the forward acquisition process into the machine learning model.

Jetraw images and functions may be used in end-to-end models to generate synthetic data with statistics matching those of genuine raw images, and play an important role in data-centric AI methodologies. Here we show how these features are used for a machine-learning task: the segmentation of cars in an urban, suburban and rural environment. Starting from a drone and airship image dataset in the Jetraw format (with calibrated sensor and optics), we use an end-to-end model to emulate realistic satellite raw images with on-demand parameters.

Interestingly, a recent metrologically accurate algorithm, offering up to 10:1 compression ratio, provides a prediction spread equivalent to that stemming from raw noise. The method described here allows to set a lower bound to the predictive uncertainty of a SL task and can be generalized to determine the statistical distortions originated from a variety of processing pipelines in AI-assisted fields.

In this work, we target the paper-to-practice gap by applying an ML4H audit framework proposed by the ITU/WHO Focus Group on Artificial Intelligence for Health (FG-AI4H) to three use cases: diagnostic prediction of diabetic retinopathy, diagnostic prediction of Alzheimer’s disease, and cytomorphologic classification for leukemia diagnostics.

The current movement towards increased use of lossy compression is highly risky, because even careful and tedious parameter tuning cannot guarantee that no applications are compromised. We implemented and validated a compression method that simultaneously provides a strong data reduction and preserves analysis results for all possible applications.

In this paper, we discuss requirements for compression tuned for machine vision, demonstrate an implementation achieving a compression ratio in the range 5:1–10:1 at a rate 200 MB/s/core in software and 400 MB/s on a VHDL FPGA simulation having a 5k-LUT footprint. We also show that adding a machine-learning component to our compressor increases the compression ratio by 10% and allows for easy portability of an otherwise complex algorithm on enterogenous architectures.