Logic-induced Diagnostic Reasoning for Semi-supervised Semantic Segmentation
This work addresses a key bottleneck in semi-supervised segmentation for computer vision applications, offering a novel integration of symbolic reasoning to enhance accuracy.
The paper tackles the problem of error accumulation in semi-supervised semantic segmentation by proposing LogicDiag, a neural-logic framework that uses symbolic knowledge to identify and resolve conflicts in pseudo labels, leading to improved performance on three standard benchmarks.
Recent advances in semi-supervised semantic segmentation have been heavily reliant on pseudo labeling to compensate for limited labeled data, disregarding the valuable relational knowledge among semantic concepts. To bridge this gap, we devise LogicDiag, a brand new neural-logic semi-supervised learning framework. Our key insight is that conflicts within pseudo labels, identified through symbolic knowledge, can serve as strong yet commonly ignored learning signals. LogicDiag resolves such conflicts via reasoning with logic-induced diagnoses, enabling the recovery of (potentially) erroneous pseudo labels, ultimately alleviating the notorious error accumulation problem. We showcase the practical application of LogicDiag in the data-hungry segmentation scenario, where we formalize the structured abstraction of semantic concepts as a set of logic rules. Extensive experiments on three standard semi-supervised semantic segmentation benchmarks demonstrate the effectiveness and generality of LogicDiag. Moreover, LogicDiag highlights the promising opportunities arising from the systematic integration of symbolic reasoning into the prevalent statistical, neural learning approaches.