PCNN: Probable-Class Nearest-Neighbor Explanations Improve Fine-Grained Image Classification Accuracy for AIs and Humans

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Giang, Nguyen, Chen, Valerie, Taesiri, Mohammad Reza, Nguyen, Anh Totti
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909296232497152
author Giang
Nguyen
Chen, Valerie
Taesiri, Mohammad Reza
Nguyen, Anh Totti
author_facet Giang
Nguyen
Chen, Valerie
Taesiri, Mohammad Reza
Nguyen, Anh Totti
contents Nearest neighbors (NN) are traditionally used to compute final decisions, e.g., in Support Vector Machines or k-NN classifiers, and to provide users with explanations for the model's decision. In this paper, we show a novel utility of nearest neighbors: To improve predictions of a frozen, pretrained image classifier C. We leverage an image comparator S that (1) compares the input image with NN images from the top-K most probable classes given by C; and (2) uses scores from S to weight the confidence scores of C to refine predictions. Our method consistently improves fine-grained image classification accuracy on CUB-200, Cars-196, and Dogs-120. Also, a human study finds that showing users our probable-class nearest neighbors (PCNN) reduces over-reliance on AI, thus improving their decision accuracy over prior work which only shows only the most-probable (top-1) class examples.
format Preprint
id arxiv_https___arxiv_org_abs_2308_13651
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle PCNN: Probable-Class Nearest-Neighbor Explanations Improve Fine-Grained Image Classification Accuracy for AIs and Humans
Giang
Nguyen
Chen, Valerie
Taesiri, Mohammad Reza
Nguyen, Anh Totti
Computer Vision and Pattern Recognition
Human-Computer Interaction
Nearest neighbors (NN) are traditionally used to compute final decisions, e.g., in Support Vector Machines or k-NN classifiers, and to provide users with explanations for the model's decision. In this paper, we show a novel utility of nearest neighbors: To improve predictions of a frozen, pretrained image classifier C. We leverage an image comparator S that (1) compares the input image with NN images from the top-K most probable classes given by C; and (2) uses scores from S to weight the confidence scores of C to refine predictions. Our method consistently improves fine-grained image classification accuracy on CUB-200, Cars-196, and Dogs-120. Also, a human study finds that showing users our probable-class nearest neighbors (PCNN) reduces over-reliance on AI, thus improving their decision accuracy over prior work which only shows only the most-probable (top-1) class examples.
title PCNN: Probable-Class Nearest-Neighbor Explanations Improve Fine-Grained Image Classification Accuracy for AIs and Humans
topic Computer Vision and Pattern Recognition
Human-Computer Interaction
url https://arxiv.org/abs/2308.13651