Browsing by Author "Wang, Yu-Chiang Frank"

Now showing 1 - 5 of 5

Detach and Adapt: Learning Cross-Domain Disentangled Deep Representation
(2018-01-01)
Liu, Yen-Cheng
;
Yeh, Yu-Ying
;
Fu, Tzu-Chien
;
Wang, Sheng-De
;
Chiu, Wei-Chen
While representation learning aims to derive interpretable features for describing visual data, representation disentanglement further results in such features so that particular image attributes can be identified and manipulated. However, one cannot easily address this task without observing ground truth annotation for the training data. To address this problem, we propose a novel deep learning model of Cross-Domain Representation Disentangler (CDRD). By observing fully annotated source-domain data and unlabeled target-domain data of interest, our model bridges the information across data domains and transfers the attribute information accordingly. Thus, cross-domain feature disentanglement and adaptation can be jointly performed. In the experiments, we provide qualitative results to verify our disentanglement capability. Moreover, we further confirm that our model can be applied for solving classification tasks of unsupervised domain adaptation, and performs favorably against state-of-the-art image disentanglement and translation methods.
DOMAIN-ADAPTIVE GENERATIVE ADVERSARIAL NETWORKS FOR SKETCH-TO-PHOTO INVERSION
(2017-01-01)
Liu, Yen-Cheng
;
Chiu, Wei-Chen
;
Wang, Sheng-De
;
Wang, Yu-Chiang Frank
;
交大名義發表
Generating photo-realistic images from multiple style sketches is one of challenging tasks in image synthesis with important applications such as facial composite for suspects. While machine learning techniques have been applied for solving this problem, the requirement of collecting sketch and face photo image pairs would limit the use of the learned model for rendering sketches of different styles. In this paper, we propose a novel deep learning model of Domain-adaptive Generative Adversarial Networks (DA-GAN). The design of DA-GAN performs cross-style sketch-to-photo inversion, which mitigates the difference across input sketch styles without the need to collect a large number of sketch and face image pairs for training purposes. In experiments, we show that our method is able to produce satisfactory results as well as performing favorably against state-of-the-art approaches.
LEARNING GUIDED CONVOLUTIONAL NEURAL NETWORKS FOR CROSS-RESOLUTION FACE RECOGNITION
(2017-01-01)
Fu, Tzu-Chien
;
Chiu, Wei-Chen
;
Wang, Yu-Chiang Frank
;
交大名義發表
;
National Chiao Tung University
Cross-resolution face recognition tackles the problem of matching face images with different resolutions. Although state-of-the-art convolutional neural network (CNN) based methods have reported promising performances on standard face recognition problems, such models cannot sufficiently describe images with resolution different from those seen during training, and thus cannot solve the above task accordingly. In this paper, we propose Guided Convolutional Neural Network (Guided-CNN), which is a novel CNN architecture with parallel sub-CNN models as guide and learners. Unique loss functions are introduced, which would serve as joint supervision for images within and across resolutions. Our experiments not only verify the use of our model for cross-resolution recognition, but also its applicability of recognizing face images with different degrees of occlusion.
LEARNING POSE-AWARE 3D RECONSTRUCTION VIA 2D-3D SELF-CONSISTENCY
(2019-01-01)
Liao, Yi-Lun
;
Yang, Yao-Cheng
;
Lin, Yuan-Fang
;
Chen, Pin-Jung
;
Kuo, Chia-Wen
3D reconstruction, inferring 3D shape information from a single 2D image, has drawn attention from learning and vision communities. In this paper, we propose a framework for learning pose-aware 3D shape reconstruction. Our proposed model learns deep representation for recovering the 3D object, with the ability to extract camera pose information but without any direct supervision of ground truth camera pose. This is realized by exploitation of 2D-3D self-consistency between 2D masks and 3D voxels. Experiments qualitatively and quantitatively demonstrate the effectiveness and robustness of our model, which performs favorably against state-of-the-art methods.
Moving foreground object detection via robust SIFT trajectories
(2013-04-01)
Sun, Shih-Wei
;
Wang, Yu-Chiang Frank
;
Huang, Fay
;
Liao, Hong-Yuan Mark
;
資訊科學與工程研究所
In this paper, we present an automatic foreground object detection method for videos captured by freely moving cameras. While we focus on extracting a single foreground object of interest throughout a video sequence, our approach does not require any training data nor the interaction by the users. Based on the SIFT correspondence across video frames, we construct robust SIFT trajectories in terms of the calculated foreground feature point probability. Our foreground feature point probability is able to determine candidate foreground feature points in each frame, without the need of user interaction such as parameter or threshold tuning. Furthermore, we propose a probabilistic consensus foreground object template (CFOT), which is directly applied to the input video for moving object detection via template matching. Our CFOT can be used to detect the foreground object in videos captured by a fast moving camera, even if the contrast between the foreground and background regions is low. Moreover, our proposed method can be generalized to foreground object detection in dynamic backgrounds, and is robust to viewpoint changes across video frames. The contribution of this paper is trifold: (1) we provide a robust decision process to detect the foreground object of interest in videos with contrast and viewpoint variations; (2) our proposed method builds longer SIFT trajectories, and this is shown to be robust and effective for object detection tasks; and (3) the construction of our CFOT is not sensitive to the initial estimation of the foreground region of interest, while its use can achieve excellent foreground object detection results on real-world video data. (c) 2012 Elsevier Inc. All rights reserved.