Joint architecture and knowledge distillation in CNN for Chinese text recognition

نویسندگان

چکیده

The distillation technique helps transform cumbersome neural networks into compact so that models can be deployed on alternative hardware devices. main advantage of distillation-based approaches include a simple training process, supported by most off-the-shelf deep learning software and no special requirements. In this paper, we propose guideline for distilling the architecture knowledge pretrained standard CNNs. proposed algorithm is first verified large-scale task: offline handwritten Chinese text recognition (HCTR). Compared with CNN in state-of-the-art system, reconstructed reduce computational cost >10×and model size >8×with negligible accuracy loss. Then, conducting experiments two additional classification task datasets: Text Wild (CTW) MNIST, demonstrate approach also successfully applied mainstream backbone networks.

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Building Efficient CNN Architecture for Offline Handwritten Chinese Character Recognition

Deep convolutional networks based methods have brought great breakthrough in images classification, which provides an end-to-end solution for handwritten Chinese character recognition(HCCR) problem through learning discriminative features automatically. Nevertheless, state-of-the-art CNNs appear to incur huge computation cost, and require the storage of a large number of parameters especially i...

متن کامل

Deep CNN based feature extractor for text-prompted speaker recognition

Deep learning is still not a very common tool in speaker verification field. We study deep convolutional neural network performance in the text-prompted speaker verification task. The prompted passphrase is segmented into word states — i.e. digits — to test each digit utterance separately. We train a single high-level feature extractor for all states and use cosine similarity metric for scoring...

متن کامل

Representing Text for Joint Embedding of Text and Knowledge Bases

Models that learn to represent textual and knowledge base relations in the same continuous latent space are able to perform joint inferences among the two kinds of relations and obtain high accuracy on knowledge base completion (Riedel et al., 2013). In this paper we propose a model that captures the compositional structure of textual relations, and jointly optimizes entity, knowledge base, and...

متن کامل

A CNN Based Scene Chinese Text Recognition Algorithm With Synthetic Data Engine

Scene text recognition plays an important role in many computer vision applications. The small size of available public available scene text datasets is the main challenge when training a text recognition CNN model. In this paper, we propose a CNN based Chinese text recognition algorithm. To enlarge the dataset for training the CNN model, we design a synthetic data engine for Chinese scene char...

متن کامل

Spatial and symbolic recognition of Chinese mosques

The history of Islam in China began when the first ambassador of Islamic caliphate in 654 AD, gained the court of the Chinese emperor. After that Islam has been spread throughout there during a century. In this study, authors try to study about how architectural elements and spatial forms are effected from Islam or Buddhist-Chinese tradition. Then, at the first it must be clear that which symbo...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Pattern Recognition

سال: 2021

ISSN: ['1873-5142', '0031-3203']

DOI: https://doi.org/10.1016/j.patcog.2020.107722