Interpretable Generative Models through Post-hoc Concept Bottlenecks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kulkarni, Akshay, Yan, Ge, Sun, Chung-En, Oikarinen, Tuomas, Weng, Tsui-Wei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909551484207104
author Kulkarni, Akshay
Yan, Ge
Sun, Chung-En
Oikarinen, Tuomas
Weng, Tsui-Wei
author_facet Kulkarni, Akshay
Yan, Ge
Sun, Chung-En
Oikarinen, Tuomas
Weng, Tsui-Wei
contents Concept bottleneck models (CBM) aim to produce inherently interpretable models that rely on human-understandable concepts for their predictions. However, existing approaches to design interpretable generative models based on CBMs are not yet efficient and scalable, as they require expensive generative model training from scratch as well as real images with labor-intensive concept supervision. To address these challenges, we present two novel and low-cost methods to build interpretable generative models through post-hoc techniques and we name our approaches: concept-bottleneck autoencoder (CB-AE) and concept controller (CC). Our proposed approaches enable efficient and scalable training without the need of real data and require only minimal to no concept supervision. Additionally, our methods generalize across modern generative model families including generative adversarial networks and diffusion models. We demonstrate the superior interpretability and steerability of our methods on numerous standard datasets like CelebA, CelebA-HQ, and CUB with large improvements (average ~25%) over the prior work, while being 4-15x faster to train. Finally, a large-scale user study is performed to validate the interpretability and steerability of our methods.
format Preprint
id arxiv_https___arxiv_org_abs_2503_19377
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Interpretable Generative Models through Post-hoc Concept Bottlenecks
Kulkarni, Akshay
Yan, Ge
Sun, Chung-En
Oikarinen, Tuomas
Weng, Tsui-Wei
Computer Vision and Pattern Recognition
Machine Learning
Concept bottleneck models (CBM) aim to produce inherently interpretable models that rely on human-understandable concepts for their predictions. However, existing approaches to design interpretable generative models based on CBMs are not yet efficient and scalable, as they require expensive generative model training from scratch as well as real images with labor-intensive concept supervision. To address these challenges, we present two novel and low-cost methods to build interpretable generative models through post-hoc techniques and we name our approaches: concept-bottleneck autoencoder (CB-AE) and concept controller (CC). Our proposed approaches enable efficient and scalable training without the need of real data and require only minimal to no concept supervision. Additionally, our methods generalize across modern generative model families including generative adversarial networks and diffusion models. We demonstrate the superior interpretability and steerability of our methods on numerous standard datasets like CelebA, CelebA-HQ, and CUB with large improvements (average ~25%) over the prior work, while being 4-15x faster to train. Finally, a large-scale user study is performed to validate the interpretability and steerability of our methods.
title Interpretable Generative Models through Post-hoc Concept Bottlenecks
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2503.19377