Pix2Code: Learning to Compose Neural Visual Concepts as Programs
Antonia Wüst, Wolfgang Stammer, Quentin Delfosse, Devendra Singh Dhami, Kristian Kersting
Abstract
The challenge in learning abstract concepts from images in an unsupervised fashion lies in the required integration of visual perception and generalizable relational reasoning. Moreover, the unsupervised nature of this task makes it necessary for human users to be able to understand a model’s learned concepts and potentially revise false behaviors. To tackle both the generalizability and interpretability constraints of visual concept learning, we propose Pix2Code, a framework that extends program synthesis to visual relational reasoning by utilizing the abilities of both explicit, compositional symbolic and implicit neural representations. This is achieved by retrieving object representations from images and synthesizing relational concepts as $\lambda$-calculus programs. We evaluate the diverse properties of Pix2Code on the challenging reasoning domains, Kandinsky Patterns, and CURI, testing its ability to identify compositional visual concepts that generalize to novel data and concept configurations. Particularly, in stark contrast to neural approaches, we show that Pix2Code’s representations remain human interpretable and can easily be revised for improved performance.
BibTeX
@InProceedings{pmlr-v244-wust24a,
title = {Pix2Code: Learning to Compose Neural Visual Concepts as Programs},
author = {W\"ust, Antonia and Stammer, Wolfgang and Delfosse, Quentin and Dhami, Devendra Singh and Kersting, Kristian},
booktitle = {Proceedings of the Fortieth Conference on Uncertainty in Artificial Intelligence},
pages = {3829--3852},
year = {2024},
editor = {Kiyavash, Negar and Mooij, Joris M.},
volume = {244},
series = {Proceedings of Machine Learning Research},
month = {15--19 Jul},
publisher = {PMLR},
pdf = {https://raw.githubusercontent.com/mlresearch/v244/main/assets/wust24a/wust24a.pdf},
url = {https://proceedings.mlr.press/v244/wust24a.html},
abstract = {The challenge in learning abstract concepts from images in an unsupervised fashion lies in the required integration of visual perception and generalizable relational reasoning. Moreover, the unsupervised nature of this task makes it necessary for human users to be able to understand a model’s learned concepts and potentially revise false behaviors. To tackle both the generalizability and interpretability constraints of visual concept learning, we propose Pix2Code, a framework that extends program synthesis to visual relational reasoning by utilizing the abilities of both explicit, compositional symbolic and implicit neural representations. This is achieved by retrieving object representations from images and synthesizing relational concepts as $\lambda$-calculus programs. We evaluate the diverse properties of Pix2Code on the challenging reasoning domains, Kandinsky Patterns, and CURI, testing its ability to identify compositional visual concepts that generalize to novel data and concept configurations. Particularly, in stark contrast to neural approaches, we show that Pix2Code’s representations remain human interpretable and can easily be revised for improved performance.}
}