# A Simple and Efficient Baseline for Data Attribution on Images

Source: [A Simple and Efficient Baseline for Data Attribution on Images](<https://www.sota2.com/research/paper/68fa71261e209131cea4f818>)

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

Data updated: 2025-10-26T01:59:40.801Z

Authors: Vasu Singla, Pedro Sandoval-Segura, Micah Goldblum, Jonas Geiping, Tom Goldstein

Published: 2023-11-03T17:29:46.000Z

## Abstract

Data attribution methods play a crucial role in understanding machine learning models, providing insight into which training data points are most responsible for model outputs during deployment. However, current state-of-the-art approaches require a large ensemble of as many as 300,000 models to accurately attribute model predictions. These approaches therefore come at a high computational cost, are memory intensive, and are hard to scale to large models or datasets. In this work, we focus on a minimalist baseline, utilizing the feature space of a backbone pretrained via self-supervised learning to perform data attribution. Our method is model-agnostic and scales easily to large datasets. We show results on CIFAR-10 and ImageNet, achieving strong performance that rivals or outperforms state-of-the-art approaches at a fraction of the compute or memory cost. Contrary to prior work, our results reinforce the intuition that a model's prediction on one image is most impacted by visually similar training samples. Our approach serves as a simple and efficient baseline for data attribution on images.

## 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.

- [Fine-grained Data Attribution on SB-Pokemon (train)](<https://www.sota2.com/research/sota/fine-grained-data-attribution-on-sb-pokemon-train.md>): Fine-grained Data Attribution; SB-Pokemon (train); Recall@10 (Subject): 22.

- [Fine-grained Data Attribution on SB-Pokemon (val)](<https://www.sota2.com/research/sota/fine-grained-data-attribution-on-sb-pokemon-val.md>): Fine-grained Data Attribution; SB-Pokemon (val); Recall@10 (Subject): 13.4.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2311.03386>)

[PDF](<https://arxiv.org/pdf/2311.03386.pdf>)
