Interpretable computer vision models explain their classifications through comparing the distances between the local embeddings of an image and a set of prototypes that represent the training data. However, these approaches introduce additional hyper-parameters that need to be tuned to apply to new datasets, scale poorly, and are more computationally intensive to train in comparison to black-box approaches. In this work, we introduce Component Features (ComFe), a highly scalable interpretable-by-design image classification head for pretrained Vision Transformers (ViTs) that can obtain competitive performance in comparison to comparable non-interpretable methods. ComFe is the first interpretable head, that we know of, and unlike other interpretable approaches, can be readily applied to large scale datasets such as ImageNet-1K. Additionally, ComFe provides improved robustness and outperforms previous interpretable approaches on key benchmark datasetsusing a consistent set of hyper-parameters and without finetuning the pretrained ViT backbone. With only global image labels and no segmentation or part annotations, ComFe can identify consistent component features within an image and determine which of these features are informative in making a prediction. Code is available atthis https URL.
View on arXiv@article{mannix2025_2403.04125,
title={ ComFe: An Interpretable Head for Vision Transformers },
author={ Evelyn J. Mannix and Liam Hodgkinson and Howard Bondell },
journal={arXiv preprint arXiv:2403.04125},
year={ 2025 }
}