Search Results for author: Abrar H. Abdulnabi

Found 4 papers, 0 papers with code

Beyond Forward Shortcuts: Fully Convolutional Master-Slave Networks (MSNets) with Backward Skip Connections for Semantic Segmentation

no code implementations18 Jul 2017 Abrar H. Abdulnabi, Stefan Winkler, Gang Wang

However, during inference the lower layers do not know about high layer features, although they contain contextual high semantics that benefit low layers to adaptively extract informative features for later layers.

Scene Parsing Semantic Segmentation

Episodic CAMN: Contextual Attention-Based Memory Networks With Iterative Feedback for Scene Labeling

no code implementations CVPR 2017 Abrar H. Abdulnabi, Bing Shuai, Stefan Winkler, Gang Wang

Scene labeling can be seen as a sequence-sequence prediction task (pixels-labels), and it is quite important to leverage relevant context to enhance the performance of pixel classification.

General Classification Scene Labeling

Multi-task CNN Model for Attribute Prediction

no code implementations4 Jan 2016 Abrar H. Abdulnabi, Gang Wang, Jiwen Lu, Kui Jia

Each CNN will generate attribute-specific feature representations, and then we apply multi-task learning on the features to predict their attributes.

Multi-Task Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.