Browsing by Author "Chiu, Wei-Chen"

Now showing 1 - 8 of 8

All about Structure: Adapting Structural Information across Domains for Boosting Semantic Segmentation
(2019-01-01)
Chang, Wei-Lun
;
Wang, Hui-Po
;
Peng, Wen-Hsiao
;
Chiu, Wei-Chen
;
交大名義發表
In this paper we tackle the problem of unsupervised domain adaptation for the task of semantic segmentation, where we attempt to transfer the knowledge learned upon synthetic datasets with ground-truth labels to real-world images without any annotation. With the hypothesis that the structural content of images is the most informative and decisive factor to semantic segmentation and can be readily shared across domains, we propose a Domain Invariant Structure Extraction (DISE) framework to disentangle images into domain-invariant structure and domain-specific texture representations, which can further realize image-translation across domains and enable label transfer to improve segmentation performance. Extensive experiments verify the effectiveness of our proposed DISE model and demonstrate its superiority over several state-of-the-art approaches.
<bold>ROBUST PARKING SPACE DETECTION CONSIDERING INTER-SPACE CORRELATION</bold>
(2007)
Wu, Qi
;
Huang, Chingchun
;
Wang, Shih-yu
;
Chiu, Wei-Chen
;
Chen, Tsuhan
A major problem in metropolitan areas is searching for parking spaces. In this paper, we propose a novel method for parking space detection. Given input video captured by a camera, we can distinguish the empty spaces from the occupied spaces by using an 8-class Support Vector Machine (SVM) classifier with probabilistic outputs. Considering the inter-space correlation, the outputs of the SVM classifier are fused together using a Markov Random Field (MRF) framework. The result is much improved detection performance, even when there are significant occlusion and shadowing effects in the scene. Experimental results are given to show the robustness of the proposed approach.
Bridging Stereo Matching and Optical Flow via Spatiotemporal Correspondence
(2019-01-01)
Lai, Hsueh-Ying
;
Tsai, Yi-Hsuan
;
Chiu, Wei-Chen
;
交大名義發表
;
National Chiao Tung University
Stereo matching and flow estimation are two essential tasks for scene understanding, spatially in 3D and temporally in motion. Existing approaches have been focused on the unsupervised setting due to the limited resource to obtain the large-scale ground truth data. To construct a self-learnable objective, co-related tasks are often linked together to form a joint framework. However, the prior work usually utilizes independent networks for each task, thus not allowing to learn shared feature representations across models. In this paper, we propose a single and principled network to jointly learn spatiotemporal correspondence for stereo matching and flow estimation, with a newly designed geometric connection as the unsupervised signal for temporally adjacent stereo pairs. We show that our method performs favorably against several state-of-the-art baselines for both unsupervised depth and flow estimation on the KITTI benchmark dataset.
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.
Plug-and-Play: Improve Depth Prediction via Sparse Data Propagation
(2019-01-01)
Wang, Tsun-Hsuan
;
Wang, Fu-En
;
Lin, Juan-Ting
;
Tsai, Yi-Hsuan
;
Chiu, Wei-Chen
We propose a novel plug-and-play (PnP) module for improving depth prediction with taking arbitrary patterns of sparse depths as input. Given any pre-trained depth prediction model, our PnP module updates the intermediate feature map such that the model outputs new depths consistent with the given sparse depths. Our method requires no additional training and can be applied to practical applications such as leveraging both RGB and sparse LiDAR points to robustly estimate dense depth map. Our approach achieves consistent improvements on various state-of-the-art methods on indoor (i.e., NYU-v2) and outdoor (i.e., KITTI) datasets. Various types of LiDARs are also synthesized in our experiments to verify the general applicability of our PnP module in practice.