Search Results for author:
Found 2 papers, 1 papers with code
Self-distillation Regularized Connectionist Temporal Classification Loss for Text Recognition: A Simple Yet Effective Approach
It incorporates a framewise regularization term in CTC loss to emphasize individual supervision, and leverages the maximizing-a-posteriori of latent alignment to solve the inconsistency problem that arises in distillation between CTC-based models.
Improving Table Structure Recognition with Visual-Alignment Sequential Coordinate Modeling
The ablation study also validates that the proposed coordinate sequence decoder and the visual-alignment loss are the keys to the success of our method.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
