MRN: Multiplexed Routing Network for Incremental Multilingual Text Recognition
This work addresses the challenge of adapting multilingual text recognition systems to new languages over time, which is incremental but offers practical benefits for applications dealing with evolving language data.
The paper tackles the problem of incremental multilingual text recognition, where languages are added in batches, by proposing a Multiplexed Routing Network to address rehearsal-imbalance and catastrophic forgetting, achieving average accuracy improvements of 10.3% to 35.8% over existing methods on MLT17 and MLT19 datasets.
Multilingual text recognition (MLTR) systems typically focus on a fixed set of languages, which makes it difficult to handle newly added languages or adapt to ever-changing data distribution. In this paper, we propose the Incremental MLTR (IMLTR) task in the context of incremental learning (IL), where different languages are introduced in batches. IMLTR is particularly challenging due to rehearsal-imbalance, which refers to the uneven distribution of sample characters in the rehearsal set, used to retain a small amount of old data as past memories. To address this issue, we propose a Multiplexed Routing Network (MRN). MRN trains a recognizer for each language that is currently seen. Subsequently, a language domain predictor is learned based on the rehearsal set to weigh the recognizers. Since the recognizers are derived from the original data, MRN effectively reduces the reliance on older data and better fights against catastrophic forgetting, the core issue in IL. We extensively evaluate MRN on MLT17 and MLT19 datasets. It outperforms existing general-purpose IL methods by large margins, with average accuracy improvements ranging from 10.3% to 35.8% under different settings. Code is available at https://github.com/simplify23/MRN.