Unsupervised Difficulty Estimation with Action Scores

TL;DR

This paper introduces an unsupervised method called action score for estimating sample difficulty during training, providing insights into model and dataset biases without requiring model modifications or external supervision.

Contribution

It presents a simple, model-agnostic difficulty scoring method based on loss accumulation, applicable to various tasks like image classification and object detection.

Findings

Action score correlates with sample difficulty and bias.

Method works without model modifications or external supervision.

Provides insights into dataset and model biases.

Abstract

Evaluating difficulty and biases in machine learning models has become of extreme importance as current models are now being applied in real-world situations. In this paper we present a simple method for calculating a difficulty score based on the accumulation of losses for each sample during training. We call this the action score. Our proposed method does not require any modification of the model neither any external supervision, as it can be implemented as callback that gathers information from the training process. We test and analyze our approach in two different settings: image classification, and object detection, and we show that in both settings the action score can provide insights about model and dataset biases.