Schema Inference for Interpretable Image Classification

TL;DR

This paper introduces schema inference, a novel approach for interpretable image classification that reconstructs neural network reasoning as graph matching, enhancing explainability and performance.

Contribution

It proposes SchemaNet, a new architecture modeling visual semantics and categories as relational graphs, and introduces Feat2Graph for capturing compositional contributions.

Findings

Achieves encouraging performance on benchmarks

Provides a clear deductive reasoning process

Enhances interpretability of image classification

Abstract

In this paper, we study a novel inference paradigm, termed as schema inference, that learns to deductively infer the explainable predictions by rebuilding the prior deep neural network (DNN) forwarding scheme, guided by the prevalent philosophical cognitive concept of schema. We strive to reformulate the conventional model inference pipeline into a graph matching policy that associates the extracted visual concepts of an image with the pre-computed scene impression, by analogy with human reasoning mechanism via impression matching. To this end, we devise an elaborated architecture, termed as SchemaNet, as a dedicated instantiation of the proposed schema inference concept, that models both the visual semantics of input instances and the learned abstract imaginations of target categories as topological relational graphs. Meanwhile, to capture and leverage the compositional contributions of visual semantics in a global view, we also introduce a universal Feat2Graph scheme in SchemaNet to establish the relational graphs that contain abundant interaction information. Both the theoretical analysis and the experimental results on several benchmarks demonstrate that the proposed schema inference achieves encouraging performance and meanwhile yields a clear picture of the deductive process leading to the predictions. Our code is available at https://github.com/zhfeing/SchemaNet-PyTorch.