LOGICSEG: Parsing Visual Semantics with Neural Logic Learning and Reasoning

TL;DR

LOGICSEG introduces a neural-logic framework for semantic segmentation that incorporates structured hierarchical knowledge and logical reasoning, improving prediction coherence and interpretability.

Contribution

It presents a novel neural-logic approach that integrates symbolic reasoning with deep learning for semantic segmentation, filling a gap in structured visual understanding.

Findings

Effective across multiple datasets and models

Enhances hierarchy-coherent predictions

Demonstrates generality and robustness

Abstract

Current high-performance semantic segmentation models are purely data-driven sub-symbolic approaches and blind to the structured nature of the visual world. This is in stark contrast to human cognition which abstracts visual perceptions at multiple levels and conducts symbolic reasoning with such structured abstraction. To fill these fundamental gaps, we devise LOGICSEG, a holistic visual semantic parser that integrates neural inductive learning and logic reasoning with both rich data and symbolic knowledge. In particular, the semantic concepts of interest are structured as a hierarchy, from which a set of constraints are derived for describing the symbolic relations and formalized as first-order logic rules. After fuzzy logic-based continuous relaxation, logical formulae are grounded onto data and neural computational graphs, hence enabling logic-induced network training. During inference, logical constraints are packaged into an iterative process and injected into the network in a form of several matrix multiplications, so as to achieve hierarchy-coherent prediction with logic reasoning. These designs together make LOGICSEG a general and compact neural-logic machine that is readily integrated into existing segmentation models. Extensive experiments over four datasets with various segmentation models and backbones verify the effectiveness and generality of LOGICSEG. We believe this study opens a new avenue for visual semantic parsing.