Now You See Me (CME): Concept-based Model Extraction
Problem — Deep Neural Network models are black boxes, which cannot be interpreted directly. As a result — it is difficult to build trust in such models. Existing methods, such as Concept Bottleneck Models, make such models more interpretable, but require a high annotation cost for annotating underlying concepts
Key Innovation — A method for generating Concept-based Models in a weakly-supervised fashion, requiring vastly fewer annotations as a result
Solution — Our Concept-based Model Extraction (CME) framework, capable of extracting Concept-based Models from pre-trained vanilla Convolutional Neural Networks (CNNs) in a semi-supervised fashion, whilst preserving end-task performance
In recent years, the realm of Explainable Artificial Intelligence (XAI) [1] has witnessed a surging interest in Concept Bottleneck Model (CBM) approaches [2]. These methods introduce an innovative model architecture, in which input images are processed in two distinct phases: concept encoding and concept processing.
0 Comments