K-LITE: Learning Transferable Visual Models with External Knowledge

TL;DR

K-LITE introduces a method to incorporate external structured knowledge from sources like WordNet and Wiktionary into visual models, enhancing their transferability and zero-shot learning capabilities in image classification and object detection.

Contribution

It proposes a scalable approach to enrich visual training data with external knowledge, improving transfer learning performance over existing methods.

Findings

Significant improvement in transfer learning accuracy.

Enhanced zero-shot and few-shot learning capabilities.

Effective use of external knowledge sources in vision models.

Abstract

The new generation of state-of-the-art computer vision systems are trained from natural language supervision, ranging from simple object category names to descriptive captions. This form of supervision ensures high generality and usability of the learned visual models, due to the broad concept coverage achieved via large-scale data collection process. Alternatively, we argue that learning with external knowledge is a promising way which leverages a much more structured source of supervision and offers sample efficiency. We propose K-LITE, a simple strategy to leverage external knowledge for building transferable visual systems: In training, it enriches entities in text with WordNet and Wiktionary knowledge, leading to an efficient and scalable approach to learning image representations that uses knowledge about the visual concepts. In evaluation, the text is also augmented with external knowledge and then used to reference learned visual concepts (or describe new ones) to enable zero-shot and few-shot transfer of the pre-trained models. We study the performance of K-LITE on two important computer vision problems, image classification and object detection, benchmarking on 20 and 13 different existing datasets, respectively. The proposed knowledge-augmented models show significant improvement in transfer learning performance over existing methods. Our code is available at https://github.com/microsoft/klite.