Object-Centric Neuro-Argumentative Learning
This addresses interpretability and reliability concerns in deep learning for image analysis, but it appears incremental as it combines existing methods (ABA and object-centric learning) on synthetic data.
The paper tackles the problem of improving the interpretability and reliability of deep learning for image analysis by introducing a Neural Argumentative Learning (NAL) architecture that integrates Assumption-Based Argumentation (ABA) with object-centric learning, and experiments on synthetic data show it can be competitive with a state-of-the-art alternative.
Over the last decade, as we rely more on deep learning technologies to make critical decisions, concerns regarding their safety, reliability and interpretability have emerged. We introduce a novel Neural Argumentative Learning (NAL) architecture that integrates Assumption-Based Argumentation (ABA) with deep learning for image analysis. Our architecture consists of neural and symbolic components. The former segments and encodes images into facts using object-centric learning, while the latter applies ABA learning to develop ABA frameworks enabling predictions with images. Experiments on synthetic data show that the NAL architecture can be competitive with a state-of-the-art alternative.