# Improving the trustworthiness of image classification models by utilizing bounding-box annotations

Source: [Improving the trustworthiness of image classification models by utilizing bounding-box annotations](<https://www.sota2.com/research/paper/68fa6a9a1e209131cea29493>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:29:26.390Z

Authors: Dharma KC, Chicheng Zhang

Published: 2021-08-15T15:09:07.000Z

## Abstract

We study utilizing auxiliary information in training data to improve the trustworthiness of machine learning models. Specifically, in the context of image classification, we propose to optimize a training objective that incorporates bounding box information, which is available in many image classification datasets. Preliminary experimental results show that the proposed algorithm achieves better performance in accuracy, robustness, and interpretability compared with baselines.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2108.10131>)

[PDF](<https://arxiv.org/pdf/2108.10131.pdf>)