Browsing by Author "Tan, Daniel Stanley"

Now showing 1 - 5 of 5

ADAPTING SEMANTIC SEGMENTATION OF URBAN SCENES VIA MASK-AWARE GATED DISCRIMINATOR
(2019-01-01)
Lin, Yong-Xiang
;
Tan, Daniel Stanley
;
Cheng, Wen-Huang
;
Hua, Kai-Lung
;
電子工程學系及電子研究所
Training a deep neural network for semantic segmentation relies on pixel-level ground truth labels for supervision. However, collecting large datasets with pixel-level annotations is very expensive and time consuming. One workaround is to utilize synthetic data where we can generate potentially unlimited data with their corresponding ground truth labels. Unfortunately, networks trained on synthetic data perform poorly on real images due to the domain shift problem. Domain adaptation techniques have shown potential in transferring the knowledge learned from synthetic data to real world data. Prior works have mostly leveraged on adversarial training to perform a global aligning of features. However, we observed that background objects have lesser variations across different domains as opposed to foreground objects. Using this insight, we propose a method for domain adaptation that models and adapts foreground objects and background objects separately. Our approach starts with a fast style transfer to match the appearance of the inputs. This is followed by a foreground adaptation module that learns a foreground mask that is used by our gated discriminator in order to adapt the foreground and background objects separately. We demonstrate in our experiments that our model outperforms several state-of-the-art baselines in terms of mean intersection over union (mIoU).
Domain Adaptation With Foreground/Background Cues and Gated Discriminators
(2020-07-01)
Lin, Yong-Xiang
;
Tan, Daniel Stanley
;
Chen, Yung-Yao
;
Huang, Ching-Chun
;
Hua, Kai-Lung
Self-driving cars leverage on semantic segmentation to understand an urban scene. However, it is costly to collect segmentation labels, thus, synthetic datasets are used to train segmentation models. Unfortunately, the synthetic to real domain shift causes these models to perform poorly. Prior works use adversarial training to align features of both synthetic and real-world images. We observe that background objects tend to be similar across domains, while foreground objects tend to have more variations. Using this insight, we propose an adaptation method that uses foreground and background cues and adapt them separately. We also propose a mask-aware gated discriminator that learns soft masks from the input foreground and background masks instead of naively performing binary masking that immediately removes information outside of the predicted masks. We evaluate our method on two different datasets and show that our method outperforms several state-of-the-art baselines, which verifies the effectiveness of our approach.
SEGMENTING HEPATIC LESIONS USING RESIDUAL ATTENTION U-NET WITH AN ADAPTIVE WEIGHTED DICE LOSS
(2019-01-01)
Liu, Yu-Cheng
;
Tan, Daniel Stanley
;
Chen, Jyh-Cheng
;
Cheng, Wen-Huang
;
Hua, Kai-Lung
We propose a novel network architecture called Residual Attention U-Net (ResAttU-Net) for segmenting hepatic lesions. Our model incorporates residual blocks that can extract more complex features as compared with traditional convolutional layers combined with a skip-connection attention module that learns to focus on the relevant features for the task of hepatic lesions segmentation. Moreover, we train our model using an adaptive weighted dice loss that prioritizes the pixels of the tumor class over the pixels of the background class. We evaluate our model on the MICCAI Liver Tumor Segmentation (LiTS) benchmark dataset. Our experimental results show that our method significantly improves upon several state-of-the-art baselines for hepatic lesion or liver tumor segmentation.
SPATIALLY-AWARE DOMAIN ADAPTATION FOR SEMANTIC SEGMENTATION OF URBAN SCENES
(2019-01-01)
Lin, Yong-Xiang
;
Tan, Daniel Stanley
;
Cheng, Wen-Huang
;
Chen, Yung-Yao
;
Hua, Kai-Lung
It is very expensive and time consuming to collect a large enough dataset with pixel-level annotations to train a semantic segmentation model. Synthetic datasets are common alternatives for training segmentation models, however models trained on synthetic data do not necessarily perform well on real world images due to the domain shift problem. Domain adaptation techniques address this problem by leveraging on adversarial training to align features. Prior works have mostly performed global feature alignment. They do not consider the positions of objects. However, objects in urban scenes are highly correlated with their spatial locations. For example, the sky will always appear on top while cars will usually appear in the middle of the image. Based on this insight, we propose a spatial-aware discriminator that accounts for the spatial prior on the objects in order to improve the feature alignment. We demonstrate in our experiments that our model outperforms several state-of-the-art baselines in terms of mean intersection over union (mIoU).
ZipNet: ZFNet-level Accuracy with 48 x Fewer Parameters
(2018-01-01)
Antioquia, Arren Matthew C.
;
Tan, Daniel Stanley
;
Azcarraga, Arnulfo
;
Cheng, Wen-Huang
;
Hua, Kai-Lung
With the introduction of Convolutional Neural Networks, models for image classification achieve higher classification accuracy. Based on the pattern of the design of CNN architectures, increasing the number of layers equates to a higher classification accuracy, but also increases the number of parameters and model size. This negatively affects the model training time, processing time, and memory requirement. We develop ZipNet, a CNN architecture with a higher classification accuracy than ZFNet, the winner of ILSVRC 2013, but with 48.5x smaller model size and 48.7x fewer parameters. The classification accuracy of ZipNet is higher than the performance of ZFNet and SqueezeNet on all configurations of the Caltech-256 dataset with varying number of training examples.