paper-with-me

홈 › Papers

MSGDD-cGAN: Multi-Scale Gradients Dual Discriminator Conditional Generative Adversarial Network

2021-09-12 · Mohammadreza Naderi, Zahra Nabizadeh, Nader Karimi, Shahram Shirani, Shadrokh Samavi

Conditional Generative Adversarial Networks (cGANs) have been used in many image processing tasks. However, they still have serious problems maintaining the balance between conditioning the output on the input and creating the output with the desired distribution based on the corresponding ground truth. The traditional cGANs, similar to most conventional GANs, suffer from vanishing gradients, which backpropagate from the discriminator to the generator. Moreover, the traditional cGANs are sensitive to architectural changes due to previously mentioned gradient problems. Therefore, balancing the architecture of the cGANs is almost impossible. Recently MSG-GAN has been proposed to stabilize the performance of the GANs by applying multiple connections between the generator and discriminator. In this work, we propose a method called MSGDD-cGAN, which first stabilizes the performance of the cGANs using multi-connections gradients flow. Secondly, the proposed network architecture balances the correlation of the output to input and the fitness of the output on the target distribution. This balance is generated by using the proposed dual discrimination procedure. We tested our model by segmentation of fetal ultrasound images. Our model shows a 3.18% increase in the F1 score comparing to the pix2pix version of cGANs.

📄 PDF Abstract BibTeX arXiv:2109.05614

Code (0)

등록된 구현이 없습니다.

Tasks

Conditional Image GenerationGenerative Adversarial NetworkImage GenerationMedical Image Segmentation

Methods 이 논문이 사용한 방법론

HuMan(Expedia)||How do I get a human at Expedia? How do I get a human at Expedia? How Do I Get a Human at Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Real-Time Help & Exclusive…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
PatchGAN 설명 없음
Concatenated Skip Connection A Concatenated Skip Connection is a type of skip connection that seeks to reuse features by concatenating them to new layers, allowing more information to be retained from…
Batch Normalization 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Sigmoid Activation 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Turning Waste into Wealth: Leveraging Low-Quality Samples for Enhancing Continuous Conditional Generative Adversarial Networks

2023-08-20 · Xin Ding, Yongwei Wang, Zuheng Xu

Continuous Conditional Generative Adversarial Networks (CcGANs) enable generative modeling conditional on continuous scalar variables (termed regression labels). However, they can produce subpar fake images due to limite…

Data Augmentation

TcGAN: Semantic-Aware and Structure-Preserved GANs with Individual Vision Transformer for Fast Arbitrary One-Shot Image Generation

2023-02-16 · Yunliang Jiang, Lili Yan, Xiongtao Zhang, Yong liu 외

One-shot image generation (OSG) with generative adversarial networks that learn from the internal patches of a given image has attracted world wide attention. In recent studies, scholars have primarily focused on extract…

Image GenerationImage HarmonizationImage Super-ResolutionSuper-Resolution

MsCGAN: Multi-scale Conditional Generative Adversarial Networks for Person Image Generation

2018-10-19 · Wei Tang, Gui Li, Xinyuan Bao, Teng Li

To synthesize high-quality person images with arbitrary poses is challenging. In this paper, we propose a novel Multi-scale Conditional Generative Adversarial Networks (MsCGAN), aiming to convert the input conditional pe…

Image Generation

VocGAN: A High-Fidelity Real-time Vocoder with a Hierarchically-nested Adversarial Network

2020-07-30 · Jinhyeok Yang, Jun-Mo Lee, Youngik Kim, Hoon-Young Cho 외

We present a novel high-fidelity real-time neural vocoder called VocGAN. A recently developed GAN-based vocoder, MelGAN, produces speech waveforms in real-time. However, it often produces a waveform that is insufficient …

CPUGPUSpeech Synthesis

Quantum State Tomography with Conditional Generative Adversarial Networks

2020-08-07 · Shahnawaz Ahmed, Carlos Sánchez Muñoz, Franco Nori, Anton Frisk Kockum

Quantum state tomography (QST) is a challenging task in intermediate-scale quantum devices. Here, we apply conditional generative adversarial networks (CGANs) to QST. In the CGAN framework, two duelling neural networks, …

Quantum State Tomography