Practical Insights of Repairing Model Problems on Image Classification

05/14/2022
by   Akihito Yoshii, et al.
0

Additional training of a deep learning model can cause negative effects on the results, turning an initially positive sample into a negative one (degradation). Such degradation is possible in real-world use cases due to the diversity of sample characteristics. That is, a set of samples is a mixture of critical ones which should not be missed and less important ones. Therefore, we cannot understand the performance by accuracy alone. While existing research aims to prevent a model degradation, insights into the related methods are needed to grasp their benefits and limitations. In this talk, we will present implications derived from a comparison of methods for reducing degradation. Especially, we formulated use cases for industrial settings in terms of arrangements of a data set. The results imply that a practitioner should care about better method continuously considering dataset availability and life cycle of an AI system because of a trade-off between accuracy and preventing degradation.

READ FULL TEXT

page 1

page 2

research
05/29/2023

Crafting Training Degradation Distribution for the Accuracy-Generalization Trade-off

Super-resolution (SR) techniques designed for real-world applications co...
research
04/04/2022

Stuttgart Open Relay Degradation Dataset (SOReDD)

Real-life industrial use cases for machine learning oftentimes involve h...
research
01/23/2021

Learning degraded image classification with restoration data fidelity

Learning-based methods especially with convolutional neural networks (CN...
research
11/18/2020

Positive-Congruent Training: Towards Regression-Free Model Updates

Reducing inconsistencies in the behavior of different versions of an AI ...
research
06/16/2019

The impact of Use Cases in real-world software development projects: A systematic mapping study

Objective: To identify and classify the positive and negative impacts of...
research
08/28/2023

Track Geometry Degradation Modelling Considering Multiple Indicators

Railway infrastructure requires effective maintenance to ensure safe and...
research
05/22/2021

A note on efficient audit sample selection

Auditing is a widely used method for quality improvement, and many guide...

Please sign up or login with your details

Forgot password? Click here to reset