Publication
Towards Adaptable and Interactive Image Captioning with Data Augmentation and Episodic Memory
Aliki Anagnostopoulou; Mareike Hartmann; Daniel Sonntag
In: Proceedings of The Fourth Workshop on Simple and Efficient Natural Language Processing (SustaiNLP). ACL Workshop on Simple and Efficient Natural Language Processing (SustaiNLP-2023), located at Annual Meeting of the Association for Computational Linguistics 2023, July 13, Toronto, Canada, Association for Computational Linguistics, 7/2023.
Abstract
Interactive machine learning (IML) is a beneficial learning paradigm in cases of limited data availability, as human feedback is incrementally integrated into the training process. In this paper, we present an IML pipeline for image captioning which allows us to incrementally adapt a pre-trained image captioning model to a new data distribution based on user input. In order to incorporate user input into the model, we explore the use of a combination of simple data augmentation methods to obtain larger data batches for each newly annotated data instance and implement continual learning methods to prevent catastrophic forgetting from repeated updates. For our experiments, we split a domain-specific image captioning dataset, namely VizWiz, into non-overlapping parts to simulate an incremental input flow for continually adapting the model to new data. We find that, while data augmentation worsens results, even when relatively small amounts of data are available, episodic memory is an effective strategy to retain knowledge from previously seen clusters.