scholarly journals Context-based Multi-stage Offline Handwritten Mathematical Symbol Recognition using Deep Learning

2019 ◽  
Author(s):  
Sui Kun Guan ◽  
Melody Moh ◽  
Teng-Sheng Moh
Keyword(s):  
Deep Learning ◽  
Symbol Recognition ◽  
Mathematical Symbol ◽  
Multi Stage

Multi-stage Deep Learning Technique for Improving Traffic Sign Recognition

2021 ◽  
Author(s):  
Pubudu Sanjeewani ◽  
Brijesh Verma ◽  
Joseph Affum
Keyword(s):  
Deep Learning ◽  
Traffic Sign Recognition ◽  
Traffic Sign ◽  
Sign Recognition ◽  
Multi Stage ◽  
Learning Technique

An Enhanced Multi-Stage Deep Learning Framework for Detecting Malicious Activities From Autonomous Vehicles

2021 ◽  
pp. 1-10
Author(s):  
Izhar Ahmed Khan ◽  
Nour Moustafa ◽  
Dechang Pi ◽  
Waqas Haider ◽  
Bentian Li ◽  
...  
Keyword(s):  
Deep Learning ◽  
Autonomous Vehicles ◽  
Learning Framework ◽  
Multi Stage

scholarly journals A Multi-Stage Advanced Deep Learning Graphics Pipeline

2021 ◽  
Author(s):  
Mark Wesley Harris ◽  
Sudhanshu Kumar Semwal
Keyword(s):  
Deep Learning ◽  
Multi Stage

Multi-stage deep learning based single-frame fringe projection 3D measurement method

2020 ◽  
Vol 49 (6) ◽  
pp. 20200023
Author(s):  
张钊 Zhao Zhang ◽  
韩博文 Bowen Han ◽  
于浩天 Haotian Yu ◽  
张毅 Yi Zhang ◽  
郑东亮 Dongliang Zheng ◽  
...  
Keyword(s):  
Deep Learning ◽  
Measurement Method ◽  
Fringe Projection ◽  
3D Measurement ◽  
Single Frame ◽  
Multi Stage

scholarly journals Multi-stage Contextual Deep Learning for Pedestrian Detection

2013 ◽  
Author(s):  
Xingyu Zeng ◽  
Wanli Ouyang ◽  
Xiaogang Wang
Keyword(s):  
Deep Learning ◽  
Pedestrian Detection ◽  
Multi Stage

scholarly journals Multi-Stage Meta-Learning for Few-Shot with Lie Group Network Constraint

2020 ◽  
Author(s):  
Fang Dong ◽  
Fanzhang Li
Keyword(s):  
Deep Learning ◽  
Gradient Descent ◽  
Large Scale ◽  
Common Knowledge ◽  
Stiefel Manifold ◽  
Training Process ◽  
Multi Stage ◽  
Training Approach ◽  
Meta Learning ◽  
Novel Method

Deep learning has achieved lots of successes in many fields, but when trainable sample are extremely limited, deep learning often under or overfitting to few samples. Meta-learning was proposed to solve difficulties in few-shot learning and fast adaptive areas. Meta-learner learns to remember some common knowledge by training on large scale tasks sampled from a certain data distribution to equip generalization when facing unseen new tasks. Due to the limitation of samples, most approaches only use shallow neural network to avoid overfitting and reduce the difficulty of training process, that causes the waste of many extra information when adapting to unseen tasks. Euclidean space-based gradient descent also make meta-learner's update inaccurate. These issues cause many meta-learning model hard to extract feature from samples and update network parameters. In this paper, we propose a novel method by using multi-stage joint training approach to post the bottleneck during adapting process. To accelerate adapt procedure, we also constraint network to Stiefel manifold, thus meta-learner could perform more stable gradient descent in limited steps. Experiment on mini-ImageNet shows that our method reaches better accuracy under 5-way 1-shot and 5-way 5-shot conditions.

Sign in / Sign up

Export Citation Format

Share Document