activity
20182025
most citedAdversarial Network with Multiple Classifiers for Open Set Domain Adaptation

103 citations · 103 across the 3 of their papers we have counts for

collaborators
Showing cs.CVShow all

7 papers · 1 filter

cs.CV2025

Evaluating the Efficacy of Sentinel-2 versus Aerial Imagery in Serrated Tussock Classification

Rezwana Sultana, Manzur Murshed, Kathryn Sheffield +3

Invasive species pose major global threats to ecosystems and agriculture. Serrated tussock (\textit{Nassella trichotoma}) is a highly competitive invasive grass species that disrup…

cs.CV2024

Hyperspectral Imaging-Based Grain Quality Assessment With Limited Labelled Data

Priyabrata Karmakar, Manzur Murshed, Shyh Wei Teng

Recently hyperspectral imaging (HSI)-based grain quality assessment has gained research attention. However, unlike other imaging modalities, HSI data lacks sufficient labelled samp…

cs.CV2021

Integrated Generalized Zero-Shot Learning for Fine-Grained Classification

Tasfia Shermin, Shyh Wei Teng, Ferdous Sohel +2

Embedding learning (EL) and feature synthesizing (FS) are two of the popular categories of fine-grained GZSL methods. EL or FS using global features cannot discriminate fine detail…

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…