SoftCTC-semi-supervised learning for text recognition using soft pseudo-labels

This paper explores semi-supervised training for sequence tasks, such as optical character recognition or automatic speech recognition. We propose a novel loss function-SoftCTC-which is an extension of CTC allowing to consider multiple transcription variants at the same time. This allows to omit the confidence-based filtering step which is otherwise a crucial component of pseudo-labeling approaches to semi-supervised learning. We demonstrate the effectiveness of our method on a challenging handwriting recognition task and conclude that SoftCTC matches the performance of a finely tuned filtering-based pipeline. We also evaluated SoftCTC in terms of computational efficiency, concluding that it is significantly more efficient than a nave CTC-based approach for training on multiple transcription variants, and we make our GPU implementation public.