DeViL: Decoding Vision features into Language

TL;DR

DeViL decodes vision features into natural language descriptions at different network layers, providing interpretable, localized explanations of vision models using a transformer-based approach that generalizes across vision backbones.

Contribution

Introduces DeViL, a method that translates vision features into language for layer-wise interpretability, leveraging a transformer and pre-trained language model for fast, open-vocabulary explanations.

Findings

Outperforms previous captioning models on CC3M.

Generates relevant textual descriptions for vision features.

Achieves state-of-the-art neuron-wise explanations on MILANNOTATIONS.

Abstract

Post-hoc explanation methods have often been criticised for abstracting away the decision-making process of deep neural networks. In this work, we would like to provide natural language descriptions for what different layers of a vision backbone have learned. Our DeViL method decodes vision features into language, not only highlighting the attribution locations but also generating textual descriptions of visual features at different layers of the network. We train a transformer network to translate individual image features of any vision layer into a prompt that a separate off-the-shelf language model decodes into natural language. By employing dropout both per-layer and per-spatial-location, our model can generalize training on image-text pairs to generate localized explanations. As it uses a pre-trained language model, our approach is fast to train, can be applied to any vision backbone, and produces textual descriptions at different layers of the vision network. Moreover, DeViL can create open-vocabulary attribution maps corresponding to words or phrases even outside the training scope of the vision model. We demonstrate that DeViL generates textual descriptions relevant to the image content on CC3M surpassing previous lightweight captioning models and attribution maps uncovering the learned concepts of the vision backbone. Finally, we show DeViL also outperforms the current state-of-the-art on the neuron-wise descriptions of the MILANNOTATIONS dataset. Code available at https://github.com/ExplainableML/DeViL