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 $\unicode{x2013}$ SoftCTC $\unicode{x2013}$ 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 na\"ive CTC-based approach for training on multiple transcription variants, and we make our GPU implementation public.
Code (1)
Tasks
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Computational EfficiencyGPUHandwriting RecognitionOptical Character RecognitionOptical Character Recognition (OCR)speech-recognitionSpeech RecognitionSimilar Papers 제목 키워드 기반
Roll With the Punches: Expansion and Shrinkage of Soft Label Selection for Semi-supervised Fine-Grained Learning
While semi-supervised learning (SSL) has yielded promising results, the more realistic SSL scenario remains to be explored, in which the unlabeled data exhibits extremely high recognition difficulty, e.g., fine-grained v…
Fine-Grained Image ClassificationSemi-Supervised Image ClassificationSS-MFAR : Semi-supervised Multi-task Facial Affect Recognition
Automatic affect recognition has applications in many areas such as education, gaming, software development, automotives, medical care, etc. but it is non trivial task to achieve appreciable performance on in-the-wild da…
Multi-Task LearningImproving End-to-End Bangla Speech Recognition with Semi-supervised Training
Automatic speech recognition systems usually require large annotated speech corpus for training. The manual annotation of a large corpus is very difficult. It can be very helpful to use unsupervised and semi-supervised l…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionSemi-supervised Federated Learning for Activity Recognition
Training deep learning models on in-home IoT sensory data is commonly used to recognise human activities. Recently, federated learning systems that use edge devices as clients to support local human activity recognition …
Activity RecognitionData AugmentationFederated LearningHuman Activity RecognitionTOWARDS ROBOT VISION MODULE DEVELOPMENT WITH EXPERIENTIAL ROBOT LEARNING
n this paper we present a thrust in three directions of visual development us- ing supervised and semi-supervised techniques. The first is an implementation of semi-supervised object detection and recognition using the p…
object-detectionObject DetectionSemi-Supervised Object Detection