CoProNN: Concept-based Prototypical Nearest Neighbors for Explaining Vision Models

TL;DR

CoProNN introduces a concept-based explanation method for vision models that uses natural language to generate visual prototypes via text-to-image models, enabling intuitive, task-specific explanations and effective human-machine collaboration.

Contribution

The paper presents a novel, modular approach that leverages text-to-image generation for creating visual prototypes, facilitating easy, domain-expert-friendly explanations for computer vision models.

Findings

Competes well with existing concept-based XAI methods on coarse tasks.

May outperform other methods on fine-grained classification.

Effective in human-machine collaboration settings.

Abstract

Mounting evidence in explainability for artificial intelligence (XAI) research suggests that good explanations should be tailored to individual tasks and should relate to concepts relevant to the task. However, building task specific explanations is time consuming and requires domain expertise which can be difficult to integrate into generic XAI methods. A promising approach towards designing useful task specific explanations with domain experts is based on compositionality of semantic concepts. Here, we present a novel approach that enables domain experts to quickly create concept-based explanations for computer vision tasks intuitively via natural language. Leveraging recent progress in deep generative methods we propose to generate visual concept-based prototypes via text-to-image methods. These prototypes are then used to explain predictions of computer vision models via a simple k-Nearest-Neighbors routine. The modular design of CoProNN is simple to implement, it is straightforward to adapt to novel tasks and allows for replacing the classification and text-to-image models as more powerful models are released. The approach can be evaluated offline against the ground-truth of predefined prototypes that can be easily communicated also to domain experts as they are based on visual concepts. We show that our strategy competes very well with other concept-based XAI approaches on coarse grained image classification tasks and may even outperform those methods on more demanding fine grained tasks. We demonstrate the effectiveness of our method for human-machine collaboration settings in qualitative and quantitative user studies. All code and experimental data can be found in our GitHub $\href{https://github.com/TeodorChiaburu/beexplainable}{repository}$.