Context-Aware Selective Label Smoothing for Calibrating Sequence Recognition Model
원문 초록
Despite the success of deep neural network (DNN) on sequential data (i.e., scene text and speech) recognition, it suffers from the over-confidence problem mainly due to overfitting in training with the cross-entropy loss, which may make the decision-making less reliable. Confidence calibration has been recently proposed as one effective solution to this problem. Nevertheless, the majority of existing confidence calibration methods aims at non-sequential data, which is limited if directly applied to sequential data since the intrinsic contextual dependency in sequences or the class-specific statistical prior is seldom exploited. To the end, we propose a Context-Aware Selective Label Smoothing (CASLS) method for calibrating sequential data. The proposed CASLS fully leverages the contextual dependency in sequences to construct confusion matrices of contextual prediction statistics over different classes. Class-specific error rates are then used to adjust the weights of smoothing strength in order to achieve adaptive calibration. Experimental results on sequence recognition tasks, including scene text recognition and speech recognition, demonstrate that our method can achieve the state-of-the-art performance.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
AUTOMATIC PRONUNCIATION MISTAKE DETECTOR PROJECT REPORT
Transformer-Based Named Entity Recognition for Automated Server Provisioning
Do You Act Like You Talk? Exploring Pose-based Driver Action Classification with Speech Recognition Networks
Watch Your Mouth: Silent Speech Recognition with Depth Sensing
Fine-Tuning Self-Supervised Learning Models for End-to-End Pronunciation Scoring
Transformer Based Punctuation Restoration for Turkish
토론
이 논문과 연결된 포럼 글이 아직 없습니다.