Improving Computer Vision Interpretability: Transparent Two-level Classification for Complex Scenes

TL;DR

This paper introduces a transparent two-level image classification method that enhances interpretability by identifying objects within images, enabling detailed analysis of visual features in political protest detection across diverse datasets.

Contribution

The paper proposes a novel two-stage classification approach that improves transparency and interpretability in image analysis by combining object detection with standard classifiers.

Findings

Object detection enhances transparency and human understanding.

The method effectively distinguishes protest images from non-protest images.

Cross-country analysis reveals variations in protest-related objects.

Abstract

Treating images as data has become increasingly popular in political science. While existing classifiers for images reach high levels of accuracy, it is difficult to systematically assess the visual features on which they base their classification. This paper presents a two-level classification method that addresses this transparency problem. At the first stage, an image segmenter detects the objects present in the image and a feature vector is created from those objects. In the second stage, this feature vector is used as input for standard machine learning classifiers to discriminate between images. We apply this method to a new dataset of more than 140,000 images to detect which ones display political protest. This analysis demonstrates three advantages to this paper's approach. First, identifying objects in images improves transparency by providing human-understandable labels for the objects shown on an image. Second, knowing these objects enables analysis of which distinguish protest images from non-protest ones. Third, comparing the importance of objects across countries reveals how protest behavior varies. These insights are not available using conventional computer vision classifiers and provide new opportunities for comparative research.