File Download
There are no files associated with this item.
Supplementary
-
Citations:
- Appears in Collections:
Conference Paper: Deep Learning for Image Recognition
Title | Deep Learning for Image Recognition |
---|---|
Authors | |
Issue Date | 2018 |
Publisher | Department of Statistics and Actuarial Science under the Kin Lam Development Fund for Data Analytics. |
Citation | Workshop on Data Science and Deep Learning (DSDL2018), Hong Kong, 7 April 2018 How to Cite? |
Abstract | With recent rapid advances in deep learning, there have been major breakthroughs in computer
vision, one of the core subareas of artificial intelligence. In this talk, I present representative
computer vision works from my research group with a focus on object recognition and scene
understanding. Specifically, I present deep learning algorithms for image classification, RGBD
scene labeling as well as salient object detection. For image classification, I introduce a deep
transfer learning scheme, called selective joint fine-tuning, for boosting the performance of
tasks with insufficient training data. In this scheme, a target learning task with insufficient
training data is carried out simultaneously with another source learning task with abundant training data. However, the source learning task only uses a subset of training data most
relevant to the target learning task. Experiments demonstrate that our deep transfer learning
scheme achieves state-of-the-art performance on multiple visual classification tasks with
insufficient training data for deep learning. |
Persistent Identifier | http://hdl.handle.net/10722/253705 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Yu, Y | - |
dc.date.accessioned | 2018-05-25T08:31:23Z | - |
dc.date.available | 2018-05-25T08:31:23Z | - |
dc.date.issued | 2018 | - |
dc.identifier.citation | Workshop on Data Science and Deep Learning (DSDL2018), Hong Kong, 7 April 2018 | - |
dc.identifier.uri | http://hdl.handle.net/10722/253705 | - |
dc.description.abstract | With recent rapid advances in deep learning, there have been major breakthroughs in computer vision, one of the core subareas of artificial intelligence. In this talk, I present representative computer vision works from my research group with a focus on object recognition and scene understanding. Specifically, I present deep learning algorithms for image classification, RGBD scene labeling as well as salient object detection. For image classification, I introduce a deep transfer learning scheme, called selective joint fine-tuning, for boosting the performance of tasks with insufficient training data. In this scheme, a target learning task with insufficient training data is carried out simultaneously with another source learning task with abundant training data. However, the source learning task only uses a subset of training data most relevant to the target learning task. Experiments demonstrate that our deep transfer learning scheme achieves state-of-the-art performance on multiple visual classification tasks with insufficient training data for deep learning. | - |
dc.language | eng | - |
dc.publisher | Department of Statistics and Actuarial Science under the Kin Lam Development Fund for Data Analytics. | - |
dc.relation.ispartof | Workshop on Data Science and Deep Learning, DSDL2018 | - |
dc.title | Deep Learning for Image Recognition | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Yu, Y: yzyu@cs.hku.hk | - |
dc.identifier.authority | Yu, Y=rp01415 | - |
dc.identifier.hkuros | 285068 | - |
dc.publisher.place | Hong Kong | - |