Explainable Concept Generation through Vision-Language Preference Learning for Understanding Neural Networks' Internal Representations
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915329442054144 |
|---|---|
| author | Taparia, Aditya Sagar, Som Senanayake, Ransalu |
| author_facet | Taparia, Aditya Sagar, Som Senanayake, Ransalu |
| contents | Understanding the inner representation of a neural network helps users improve models. Concept-based methods have become a popular choice for explaining deep neural networks post-hoc because, unlike most other explainable AI techniques, they can be used to test high-level visual "concepts" that are not directly related to feature attributes. For instance, the concept of "stripes" is important to classify an image as a zebra. Concept-based explanation methods, however, require practitioners to guess and manually collect multiple candidate concept image sets, making the process labor-intensive and prone to overlooking important concepts. Addressing this limitation, in this paper, we frame concept image set creation as an image generation problem. However, since naively using a standard generative model does not result in meaningful concepts, we devise a reinforcement learning-based preference optimization (RLPO) algorithm that fine-tunes a vision-language generative model from approximate textual descriptions of concepts. Through a series of experiments, we demonstrate our method's ability to efficiently and reliably articulate diverse concepts that are otherwise challenging to craft manually. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_13438 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Explainable Concept Generation through Vision-Language Preference Learning for Understanding Neural Networks' Internal Representations Taparia, Aditya Sagar, Som Senanayake, Ransalu Computer Vision and Pattern Recognition Machine Learning Understanding the inner representation of a neural network helps users improve models. Concept-based methods have become a popular choice for explaining deep neural networks post-hoc because, unlike most other explainable AI techniques, they can be used to test high-level visual "concepts" that are not directly related to feature attributes. For instance, the concept of "stripes" is important to classify an image as a zebra. Concept-based explanation methods, however, require practitioners to guess and manually collect multiple candidate concept image sets, making the process labor-intensive and prone to overlooking important concepts. Addressing this limitation, in this paper, we frame concept image set creation as an image generation problem. However, since naively using a standard generative model does not result in meaningful concepts, we devise a reinforcement learning-based preference optimization (RLPO) algorithm that fine-tunes a vision-language generative model from approximate textual descriptions of concepts. Through a series of experiments, we demonstrate our method's ability to efficiently and reliably articulate diverse concepts that are otherwise challenging to craft manually. |
| title | Explainable Concept Generation through Vision-Language Preference Learning for Understanding Neural Networks' Internal Representations |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2408.13438 |