Posthoc Interpretation via Quantization
This addresses the need for better interpretability in machine learning models, particularly for users who rely on understanding classifier decisions, though it appears incremental as it builds on existing interpretation techniques.
The paper tackles the problem of interpreting decisions made by trained classifiers by introducing Posthoc Interpretation via Quantization (PIQ), which uses vector quantization to create a discrete, class-specific latent space; the method was evaluated on black-and-white images, color images, and audio, and found to generate interpretations that are more easily understood by participants compared to other methods.
In this paper, we introduce a new approach, called Posthoc Interpretation via Quantization (PIQ), for interpreting decisions made by trained classifiers. Our method utilizes vector quantization to transform the representations of a classifier into a discrete, class-specific latent space. The class-specific codebooks act as a bottleneck that forces the interpreter to focus on the parts of the input data deemed relevant by the classifier for making a prediction. Our model formulation also enables learning concepts by incorporating the supervision of pretrained annotation models such as state-of-the-art image segmentation models. We evaluated our method through quantitative and qualitative studies involving black-and-white images, color images, and audio. As a result of these studies we found that PIQ generates interpretations that are more easily understood by participants to our user studies when compared to several other interpretation methods in the literature.