Reciprocal Feature Learning via Explicit and Implicit Tasks in Scene Text Recognition
This work addresses scene text recognition, a key problem in computer vision for applications like document analysis, but it is incremental as it builds on existing methods by adding a complementary task.
The authors tackled scene text recognition by introducing an auxiliary character counting task without extra annotation, enhancing feature learning through reciprocal interaction between explicit and implicit tasks. Experiments on 7 benchmarks showed improved performance in both text recognition and character counting.
Text recognition is a popular topic for its broad applications. In this work, we excavate the implicit task, character counting within the traditional text recognition, without additional labor annotation cost. The implicit task plays as an auxiliary branch for complementing the sequential recognition. We design a two-branch reciprocal feature learning framework in order to adequately utilize the features from both the tasks. Through exploiting the complementary effect between explicit and implicit tasks, the feature is reliably enhanced. Extensive experiments on 7 benchmarks show the advantages of the proposed methods in both text recognition and the new-built character counting tasks. In addition, it is convenient yet effective to equip with variable networks and tasks. We offer abundant ablation studies, generalizing experiments with deeper understanding on the tasks. Code is available.