Browsing by Author "Vu-Hoang Tran"

Now showing 1 - 2 of 2

Domain Adaptation Meets Disentangled Representation Learning and Style Transfer
(2019-01-01)
Vu-Hoang Tran
;
Huang, Ching-Chun
;
資訊工程學系
;
Department of Computer Science
In this paper, we face the challenges of unsupervised domain adaptation and propose a novel three-in-one framework where three tasks - domain adaptation, disentangled representation, and style transfer are considered simultaneously. Firstly, the learned features are disentangled into common parts and specific parts. The common parts represent the transferrable features, which are suitable for domain adaptation with less negative transfer. Conversely, the specific parts characterize the unique style of each individual domain. Based on this, the new concept of feature exchange across domains, which can not only enhance the transferability of common features but also be useful for image style transfer, is introduced. These designs allow us to introduce five types of training objectives to realize the three challenging tasks at the same time. The experimental results show that our architecture can be adaptive well to full transfer learning and partial transfer learning upon a well-learned disentangled representation. Besides, the trained network also demonstrates high potential to generate style-transferred images.
IUML: INCEPTION U-NET BASED MULTI-TASK LEARNING FOR DENSITY LEVEL CLASSIFICATION AND CROWD DENSITY ESTIMATION
(2019-01-01)
Huynh, Van-Su
;
Vu-Hoang Tran
;
Huang, Ching-Chun
;
交大名義發表
;
National Chiao Tung University
Nowadays, image-based people counting is an essential technique for public safety management. However, this work is still extremely challenging due to many kinds of scale issues caused by different congested scenes, different viewing points, different image sizes, and different density levels. In this paper, we proposed a CNNs-based framework for people counting and crowd density map estimation with the consideration of the scale problems. First, we introduced an encoder-decoder architecture, which is composed of Inception modules to learn the multi-scale feature representations. Besides, to be adaptive to image resolution, a multi-loss setting over different resolutions of density maps is designed for network training. Second, we apply multi-task learning to learn the joint features for the density map estimation task and the density level classification task. This helps to enhance the feature generality under different scenes. Finally, by adopting the U-net architecture, the encoder and decoder features are then fused to generate high-resolution density maps. The efficacy of the proposed method is evaluated in the extensive experiments by quantifying the counting performance through multiple evaluation criteria.