activity
20182021
most citedAdversarial Network with Multiple Classifiers for Open Set Domain Adaptation

103 citations · 118 across the 4 of their papers we have counts for

collaborators

8 papers

cs.CV20214 cited

Anti-aliasing Deep Image Classifiers using Novel Depth Adaptive Blurring and Activation Function

Md Tahmid Hossain, Shyh Wei Teng, Ferdous Sohel +1

Deep convolutional networks are vulnerable to image translation or shift, partly due to common down-sampling layers, e.g., max-pooling and strided convolution. These operations vio…

cs.SD202111 cited

Thank you for Attention: A survey on Attention-based Artificial Neural Networks for Automatic Speech Recognition

Priyabrata Karmakar, Shyh Wei Teng, Guojun Lu

Attention is a very popular and effective mechanism in artificial neural network-based sequence-to-sequence models. In this survey paper, a comprehensive review of the different at…

cs.CV2020

Bidirectional Mapping Coupled GAN for Generalized Zero-Shot Learning

Tasfia Shermin, Shyh Wei Teng, Ferdous Sohel +2

Bidirectional mapping-based generalized zero-shot learning (GZSL) methods rely on the quality of synthesized features to recognize seen and unseen data. Therefore, learning a joint…

cs.CV2020103 cited

Adversarial Network with Multiple Classifiers for Open Set Domain Adaptation

Tasfia Shermin, Guojun Lu, Shyh Wei Teng +2

Domain adaptation aims to transfer knowledge from a domain with adequate labeled samples to a domain with scarce labeled samples. Prior research has introduced various open set dom…

cs.CV2019

Enhanced Transfer Learning with ImageNet Trained Classification Layer

Tasfia Shermin, Shyh Wei Teng, Manzur Murshed +3

Parameter fine tuning is a transfer learning approach whereby learned parameters from pre-trained source network are transferred to the target network followed by fine-tuning. Prio…

cs.CV2018

Transfer Learning Using Classification Layer Features of CNN

Tasfia Shermin, Manzur Murshed, Guojun Lu +1

Although CNNs have gained the ability to transfer learned knowledge from source task to target task by virtue of large annotated datasets but consume huge processing time to fine-t…