Losing Confidence in Quality: Unspoken Evolution of Computer Vision Services

TL;DR

This paper investigates the evolution and consistency risks of cloud-based computer vision AI services over time, revealing significant behavioral inconsistencies and communication gaps that impact reliability and maintenance.

Contribution

It provides an empirical evaluation of the behavioral evolution of computer vision services and offers recommendations for improving transparency and risk management.

Findings

Inconsistencies in service responses over 11 months

Evidence of evolution risk in AI responses

Lack of clear documentation on service changes

Abstract

Recent advances in artificial intelligence (AI) and machine learning (ML), such as computer vision, are now available as intelligent services and their accessibility and simplicity is compelling. Multiple vendors now offer this technology as cloud services and developers want to leverage these advances to provide value to end-users. However, there is no firm investigation into the maintenance and evolution risks arising from use of these intelligent services; in particular, their behavioural consistency and transparency of their functionality. We evaluated the responses of three different intelligent services (specifically computer vision) over 11 months using 3 different data sets, verifying responses against the respective documentation and assessing evolution risk. We found that there are: (1) inconsistencies in how these services behave; (2) evolution risk in the responses; and (3) a lack of clear communication that documents these risks and inconsistencies. We propose a set of recommendations to both developers and intelligent service providers to inform risk and assist maintainability.