# RATT: Recurrent Attention to Transient Tasks for Continual Image Captioning Source: [RATT: Recurrent Attention to Transient Tasks for Continual Image Captioning]() Collection index: [llms.txt]() Data updated: 2025-10-25T22:40:59.400Z Authors: Riccardo Del Chiaro, Bart{\\l}omiej Twardowski, Andrew D. Bagdanov, Joost van de Weijer Published: 2020-07-13T09:52:37.000Z ## Abstract Research on continual learning has led to a variety of approaches to mitigating catastrophic forgetting in feed-forward classification networks. Until now surprisingly little attention has been focused on continual learning of recurrent models applied to problems like image captioning. In this paper we take a systematic look at continual learning of LSTM-based models for image captioning. We propose an attention-based approach that explicitly accommodates the transient nature of vocabularies in continual image captioning tasks -- i.e. that task vocabularies are not disjoint. We call our method Recurrent Attention to Transient Tasks (RATT), and also show how to adapt continual learning approaches based on weight egularization and knowledge distillation to recurrent continual learning problems. We apply our approaches to incremental image captioning problem on two new continual learning benchmarks we define using the MS-COCO and Flickr30 datasets. Our results demonstrate that RATT is able to sequentially learn five captioning tasks while incurring no forgetting of previously learned ones. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()