Document Details

Document Type : Article In Conference 
Document Title :
Deep Model Based Transfer and Multi-Task Learning for Biological Image Analysis
Deep Model Based Transfer and Multi-Task Learning for Biological Image Analysis
 
Document Language : English 
Abstract : A central theme in learning from image data is to develop appropriate image representations for the specific task at hand. Traditional methods used handcrafted local features combined with high-level image representations to generate image-level representations. Thus, a practical challenge is to determine what features are appropriate for specific tasks. For example, in the study of gene expression patterns in Drosophila melanogaster, texture features based on wavelets were particularly effective for determining the developmental stages from in situ hybridization (ISH) images. Such image representation is however not suitable for controlled vocabulary (CV) term annotation because each CV term is often associated with only a part of an image. Here, we developed problem-independent feature extraction methods to generate hierarchical representations for ISH images. Our approach is based on the deep convolutional neural networks (CNNs) that can act on image pixels directly. To make the extracted features generic, the models were trained using a natural image set with millions of labeled examples. These models were transferred to the ISH image domain and used directly as feature extractors to compute image representations. Furthermore, we employed multi-task learning method to fine-tune the pre-trained models with labeled ISH images, and also extracted features from the fine-tuned models. Experimental results showed that feature representations computed by deep models based on transfer and multi-task learning significantly outperformed other methods for annotating gene expression patterns at different stage ranges. We also demonstrated that the intermediate layers of deep models produced the best gene expression pattern representations. 
Conference Name : KDD '15 Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 
Duration : From : 1436 AH - To : 1436 AH
From : 2015 AD - To : 2015 AD 
Publishing Year : 1436 AH
2015 AD 
Article Type : Article 
Added Date : Sunday, May 1, 2016 

Researchers

Researcher Name (Arabic)Researcher Name (English)Researcher TypeDr GradeEmail
Wenlu ZhangZhang, Wenlu Investigator  
Rongjian LiLi, Rongjian Researcher  
Tao ZengZeng, Tao Researcher  
Qian SunSun, Qian Researcher  
Sudhir KumarKumar, Sudhir Researcher  
Jieping YeYe, Jieping Researcher  
Shuiwang JiJi, Shuiwang Researcher  

Files

File NameTypeDescription
 38780.pdf pdf 

Back To Researches Page