Explainable Deep Classification Models for Domain Generalization
This work addresses the problem of domain generalization for object classification by enhancing explainability, offering a novel approach that could benefit AI systems in varied visual domains.
The authors tackled the trade-off between explainability and accuracy in deep classification models by developing a training strategy that enforces saliency-based feedback, resulting in no perceptible accuracy degradation while improving explainability and domain generalization.
Conventionally, AI models are thought to trade off explainability for lower accuracy. We develop a training strategy that not only leads to a more explainable AI system for object classification, but as a consequence, suffers no perceptible accuracy degradation. Explanations are defined as regions of visual evidence upon which a deep classification network makes a decision. This is represented in the form of a saliency map conveying how much each pixel contributed to the network's decision. Our training strategy enforces a periodic saliency-based feedback to encourage the model to focus on the image regions that directly correspond to the ground-truth object. We quantify explainability using an automated metric, and using human judgement. We propose explainability as a means for bridging the visual-semantic gap between different domains where model explanations are used as a means of disentagling domain specific information from otherwise relevant features. We demonstrate that this leads to improved generalization to new domains without hindering performance on the original domain.