SoftCTC x2013 Semi-Supervised Learning for Text Recognition using Soft Pseudo-Labels
share
This paper explores semi-supervised training for sequence tasks, such as Optical Character Recognition or Automatic Speech Recognition. We propose a novel loss function x2013 SoftCTC x2013 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 naïve CTC-based approach for training on multiple transcription variants, and we make our GPU implementation public.
READ FULL TEXT