cs.CVJun 19, 2025

Neurosymbolic Object-Centric Learning with Distant Supervision

Authors: Stefano Colamonaco, David Debot, Giuseppe Marra

Organizations: Department of Computer Science, KU Leuven

Abstract

Neurosymbolic learning can use symbolic rules to provide supervision for latent concepts from weak labels, but it commonly assumes that the entities referenced by these rules are already specified. Object-centric models decompose images into slot-like representations; however, such slots are not necessarily aligned with the predicates required for symbolic reasoning. We investigate object-centric neurosymbolic learning under distant supervision, where the object-level arguments of a logic program are learned directly from images using only global task labels. We introduce DeepPbjectLog, a probabilistic neurosymbolic model that integrates a slot-based perceptual encoder with a probabilistic logic layer. The encoder predicts objectness and class probabilities for candidate object representations, while the logic layer marginalizes over latent objectness and class assignments to compute the likelihood of the observed label. This formulation provides a differentiable task-level learning signal for object-centric perception without requiring per-object labels, masks, bounding boxes, or heuristic set matching. Evaluations across diverse visual reasoning tasks demonstrate that DeepObjectLog achieves superior out-of-distribution generalization to compositional, object-count, and rule shifts compared to neural object-centric and standard neurosymbolic baselines.

Figures & tables

Appendix figures & tables17 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Weakly Supervised Concept Learning for Object-centric Visual Reasoning

    May 5, 2026Sparsh Tiwari, Bettina Finzel, Gesina SchwalbeVisual ReasoningObject-Centric Representation Learning

  2. Weakly supervised concept Bottleneck Learning for Robust Two stage Object centric visual reasoning

    Aug 23, 2026Sparsh Tiwari, Gesina Schwalbe, Bettina FinzelConcept Bottleneck ModelsObject-Centric Representation Learning

  3. Soft Symbol Grounding for Prototypical Concepts

    Sep 10, 2026Marcos Galván-López, Nijesh Upreti, Hiram Calvo +2Prototype-Based ClassificationWeakly Supervised Learning