The Experts below are selected from a list of 20214 Experts worldwide ranked by ideXlab platform
Yi Yang - One of the best experts on this subject based on the ideXlab platform.
-
macro micro adversarial network for human parsing
European Conference on Computer Vision, 2018Co-Authors: Yawei Luo, Zhedong Zheng, Liang Zheng, Tao Guan, Yi YangAbstract:In human parsing, the pixel-wise classification loss has drawbacks in its low-level local inconsistency and high-level semantic inconsistency. The introduction of the adversarial network tackles the two problems using a single Discriminator. However, the two types of parsing inconsistency are generated by distinct mechanisms, so it is difficult for a single Discriminator to solve them both. To address the two kinds of inconsistencies, this paper proposes the Macro-Micro Adversarial Net (MMAN). It has two Discriminators. One Discriminator, Macro D, acts on the low-resolution label map and penalizes semantic inconsistency, e.g., misplaced body parts. The other Discriminator, Micro D, focuses on multiple patches of the high-resolution label map to address the local inconsistency, e.g., blur and hole. Compared with traditional adversarial networks, MMAN not only enforces local and semantic consistency explicitly, but also avoids the poor convergence problem of adversarial networks when handling high resolution images. In our experiment, we validate that the two Discriminators are complementary to each other in improving the human parsing accuracy. The proposed framework is capable of producing competitive parsing performance compared with the state-of-the-art methods, i.e., mIoU = 46.81% and 59.91% on LIP and PASCAL-Person-Part, respectively. On a relatively small dataset PPSS, our pre-trained model demonstrates impressive generalization ability. The code is publicly available at https://github.com/RoyalVane/MMAN.
-
macro micro adversarial network for human parsing
arXiv: Computer Vision and Pattern Recognition, 2018Co-Authors: Yawei Luo, Zhedong Zheng, Liang Zheng, Tao Guan, Yi YangAbstract:In human parsing, the pixel-wise classification loss has drawbacks in its low-level local inconsistency and high-level semantic inconsistency. The introduction of the adversarial network tackles the two problems using a single Discriminator. However, the two types of parsing inconsistency are generated by distinct mechanisms, so it is difficult for a single Discriminator to solve them both. To address the two kinds of inconsistencies, this paper proposes the Macro-Micro Adversarial Net (MMAN). It has two Discriminators. One Discriminator, Macro D, acts on the low-resolution label map and penalizes semantic inconsistency, e.g., misplaced body parts. The other Discriminator, Micro D, focuses on multiple patches of the high-resolution label map to address the local inconsistency, e.g., blur and hole. Compared with traditional adversarial networks, MMAN not only enforces local and semantic consistency explicitly, but also avoids the poor convergence problem of adversarial networks when handling high resolution images. In our experiment, we validate that the two Discriminators are complementary to each other in improving the human parsing accuracy. The proposed framework is capable of producing competitive parsing performance compared with the state-of-the-art methods, i.e., mIoU=46.81% and 59.91% on LIP and PASCAL-Person-Part, respectively. On a relatively small dataset PPSS, our pre-trained model demonstrates impressive generalization ability. The code is publicly available at this https URL.
Taylor Bergkirkpatrick - One of the best experts on this subject based on the ideXlab platform.
-
unsupervised text style transfer using language models as Discriminators
Neural Information Processing Systems, 2018Co-Authors: Zichao Yang, Eric Po Xing, Zhiting Hu, Chris Dyer, Taylor BergkirkpatrickAbstract:Binary classifiers are employed as Discriminators in GAN-based unsupervised style transfer models to ensure that transferred sentences are similar to sentences in the target domain. One difficulty with the binary Discriminator is that error signal is sometimes insufficient to train the model to produce rich-structured language. In this paper, we propose a technique of using a target domain language model as the Discriminator to provide richer, token-level feedback during the learning process. Because our language model scores sentences directly using a product of locally normalized probabilities, it offers more stable and more useful training signal to the generator. We train the generator to minimize the negative log likelihood (NLL) of generated sentences evaluated by a language model. By using continuous approximation of the discrete samples, our model can be trained using back-propagation in an end-to-end way. Moreover, we find empirically with a language model as a structured Discriminator, it is possible to eliminate the adversarial training steps using negative samples, thus making training more stable. We compare our model with previous work using convolutional neural networks (CNNs) as Discriminators and show our model outperforms them significantly in three tasks including word substitution decipherment, sentiment modification and related language translation.
Zhaoyan Ming - One of the best experts on this subject based on the ideXlab platform.
-
deeppoison feature transfer based stealthy poisoning attack for dnns
IEEE Transactions on Circuits and Systems Ii-express Briefs, 2021Co-Authors: Jinyin Chen, Longyuan Zhang, Haibin Zheng, Xueke Wang, Zhaoyan MingAbstract:Deep neural networks are susceptible to poisoning attacks by purposely polluted training data with specific triggers. As existing episodes mainly focused on attack success rate with patch-based samples, defense algorithms can easily detect these poisoning samples. We propose DeepPoison, a novel adversarial network of one generator and two Discriminators, to address this problem. Specifically, the generator automatically extracts the target class' hidden features and embeds them into benign training samples. One Discriminator controls the ratio of the poisoning perturbation. The other Discriminator works as the target model to testify the poisoning effects. The novelty of DeepPoison lies in that the generated poisoned training samples are indistinguishable from the benign ones by both defensive methods and manual visual inspection, and even benign test samples can achieve the attack. Extensive experiments have shown that DeepPoison can achieve a state-of-the-art attack success rate, as high as 91.74%, with only 7% poisoned samples on publicly available datasets LFW and CASIA. Furthermore, we have experimented with high-performance defense algorithms such as autodecoder defense and DBSCAN cluster detection and showed the resilience of DeepPoison.
-
deeppoison feature transfer based stealthy poisoning attack
arXiv: Cryptography and Security, 2021Co-Authors: Jinyin Chen, Longyuan Zhang, Haibin Zheng, Xueke Wang, Zhaoyan MingAbstract:Deep neural networks are susceptible to poisoning attacks by purposely polluted training data with specific triggers. As existing episodes mainly focused on attack success rate with patch-based samples, defense algorithms can easily detect these poisoning samples. We propose DeepPoison, a novel adversarial network of one generator and two Discriminators, to address this problem. Specifically, the generator automatically extracts the target class' hidden features and embeds them into benign training samples. One Discriminator controls the ratio of the poisoning perturbation. The other Discriminator works as the target model to testify the poisoning effects. The novelty of DeepPoison lies in that the generated poisoned training samples are indistinguishable from the benign ones by both defensive methods and manual visual inspection, and even benign test samples can achieve the attack. Extensive experiments have shown that DeepPoison can achieve a state-of-the-art attack success rate, as high as 91.74%, with only 7% poisoned samples on publicly available datasets LFW and CASIA. Furthermore, we have experimented with high-performance defense algorithms such as autodecoder defense and DBSCAN cluster detection and showed the resilience of DeepPoison.
Yawei Luo - One of the best experts on this subject based on the ideXlab platform.
-
macro micro adversarial network for human parsing
European Conference on Computer Vision, 2018Co-Authors: Yawei Luo, Zhedong Zheng, Liang Zheng, Tao Guan, Yi YangAbstract:In human parsing, the pixel-wise classification loss has drawbacks in its low-level local inconsistency and high-level semantic inconsistency. The introduction of the adversarial network tackles the two problems using a single Discriminator. However, the two types of parsing inconsistency are generated by distinct mechanisms, so it is difficult for a single Discriminator to solve them both. To address the two kinds of inconsistencies, this paper proposes the Macro-Micro Adversarial Net (MMAN). It has two Discriminators. One Discriminator, Macro D, acts on the low-resolution label map and penalizes semantic inconsistency, e.g., misplaced body parts. The other Discriminator, Micro D, focuses on multiple patches of the high-resolution label map to address the local inconsistency, e.g., blur and hole. Compared with traditional adversarial networks, MMAN not only enforces local and semantic consistency explicitly, but also avoids the poor convergence problem of adversarial networks when handling high resolution images. In our experiment, we validate that the two Discriminators are complementary to each other in improving the human parsing accuracy. The proposed framework is capable of producing competitive parsing performance compared with the state-of-the-art methods, i.e., mIoU = 46.81% and 59.91% on LIP and PASCAL-Person-Part, respectively. On a relatively small dataset PPSS, our pre-trained model demonstrates impressive generalization ability. The code is publicly available at https://github.com/RoyalVane/MMAN.
-
macro micro adversarial network for human parsing
arXiv: Computer Vision and Pattern Recognition, 2018Co-Authors: Yawei Luo, Zhedong Zheng, Liang Zheng, Tao Guan, Yi YangAbstract:In human parsing, the pixel-wise classification loss has drawbacks in its low-level local inconsistency and high-level semantic inconsistency. The introduction of the adversarial network tackles the two problems using a single Discriminator. However, the two types of parsing inconsistency are generated by distinct mechanisms, so it is difficult for a single Discriminator to solve them both. To address the two kinds of inconsistencies, this paper proposes the Macro-Micro Adversarial Net (MMAN). It has two Discriminators. One Discriminator, Macro D, acts on the low-resolution label map and penalizes semantic inconsistency, e.g., misplaced body parts. The other Discriminator, Micro D, focuses on multiple patches of the high-resolution label map to address the local inconsistency, e.g., blur and hole. Compared with traditional adversarial networks, MMAN not only enforces local and semantic consistency explicitly, but also avoids the poor convergence problem of adversarial networks when handling high resolution images. In our experiment, we validate that the two Discriminators are complementary to each other in improving the human parsing accuracy. The proposed framework is capable of producing competitive parsing performance compared with the state-of-the-art methods, i.e., mIoU=46.81% and 59.91% on LIP and PASCAL-Person-Part, respectively. On a relatively small dataset PPSS, our pre-trained model demonstrates impressive generalization ability. The code is publicly available at this https URL.
Zichao Yang - One of the best experts on this subject based on the ideXlab platform.
-
unsupervised text style transfer using language models as Discriminators
Neural Information Processing Systems, 2018Co-Authors: Zichao Yang, Eric Po Xing, Zhiting Hu, Chris Dyer, Taylor BergkirkpatrickAbstract:Binary classifiers are employed as Discriminators in GAN-based unsupervised style transfer models to ensure that transferred sentences are similar to sentences in the target domain. One difficulty with the binary Discriminator is that error signal is sometimes insufficient to train the model to produce rich-structured language. In this paper, we propose a technique of using a target domain language model as the Discriminator to provide richer, token-level feedback during the learning process. Because our language model scores sentences directly using a product of locally normalized probabilities, it offers more stable and more useful training signal to the generator. We train the generator to minimize the negative log likelihood (NLL) of generated sentences evaluated by a language model. By using continuous approximation of the discrete samples, our model can be trained using back-propagation in an end-to-end way. Moreover, we find empirically with a language model as a structured Discriminator, it is possible to eliminate the adversarial training steps using negative samples, thus making training more stable. We compare our model with previous work using convolutional neural networks (CNNs) as Discriminators and show our model outperforms them significantly in three tasks including word substitution decipherment, sentiment modification and related language translation.
