But that's not why: Inference adjustment by interactive prototype deselection

03/18/2022
by   Michael Gerstenberger, et al.
0

Despite significant advances in machine learning, decision-making of artificial agents is still not perfect and often requires post-hoc human interventions. If the prediction of a model relies on unreasonable factors it is desirable to remove their effect. Deep interactive prototype adjustment enables the user to give hints and correct the model's reasoning. In this paper, we demonstrate that prototypical-part models are well suited for this task as their prediction is based on prototypical image patches that can be interpreted semantically by the user. It shows that even correct classifications can rely on unreasonable prototypes that result from confounding variables in a dataset. Hence, we propose simple yet effective interaction schemes for inference adjustment: The user is consulted interactively to identify faulty prototypes. Non-object prototypes can be removed by prototype masking or a custom mode of deselection training. Interactive prototype rejection allows machine learning naïve users to adjust the logic of reasoning without compromising the accuracy.

READ FULL TEXT

page 3

page 4

research
06/13/2022

Estimating Causal Effects Under Image Confounding Bias with an Application to Poverty in Africa

Observational studies of causal effects require adjustment for confoundi...
research
05/11/2023

Image-to-Text Translation for Interactive Image Recognition: A Comparative User Study with Non-Expert Users

Interactive machine learning (IML) allows users to build their custom ma...
research
10/13/2017

User Modelling for Avoiding Overfitting in Interactive Knowledge Elicitation for Prediction

In human-in-the-loop machine learning, the user provides information bey...
research
09/24/2019

Selecting a Scale for Spatial Confounding Adjustment

Unmeasured, spatially-structured factors can confound associations betwe...
research
12/04/2021

Interactive Disentanglement: Learning Concepts by Interacting with their Prototype Representations

Learning visual concepts from raw images without strong supervision is a...
research
08/02/2022

Gesture-aware Interactive Machine Teaching with In-situ Object Annotations

Interactive Machine Teaching (IMT) systems allow non-experts to easily c...
research
03/03/2015

The Bayesian Case Model: A Generative Approach for Case-Based Reasoning and Prototype Classification

We present the Bayesian Case Model (BCM), a general framework for Bayesi...

Please sign up or login with your details

Forgot password? Click here to reset