Pix2Code: Learning to Compose Neural Visual Concepts as Programs
This addresses the challenge of interpretable and generalizable visual concept learning for AI systems, though it is incremental as it builds on program synthesis methods.
The authors tackled the problem of unsupervised learning of abstract visual concepts by integrating visual perception and relational reasoning, proposing Pix2Code to synthesize concepts as programs, which achieved human-interpretable representations that can be revised for improved performance.
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 learnt concepts and potentially revise false behaviours. 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, thereby 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 be easily revised for improved performance.