Generative Adversarial Network Architectures For Image Synthesis Using Capsule Networks
Generative Adversarial Network Architectures For Image Synthesis Using Capsule Networks 類似於SAGAN的出發點，傳統CNN僅僅考慮圖像的局部信息，沒有考慮全局範圍內不同區域的聯繫，而capsule是可以建模圖像的空域相關性的，因此用capsule network代替CNN作爲判別器，使生成的圖像具有結構性。
相關文章
- 1. Generative Adversarial Text to Image Synthesis
- 2. [Style Transfer]——Blood Vessel Geometry Synthesis using Generative Adversarial Networks
- 3. Generative Adversarial Networks for Hyperspectral Image Classification
- 4. Binary Generative Adversarial Networks for Image Retrieval
- 5. Bi-Modality Medical Image Synthesis Using Semi-Supervised Sequential Generative Adversarial Networks
- 6. CartoonGAN: Generative Adversarial Networks for Photo Cartoonization
- 7. DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis 論文解讀
- 8. [TMI2019-07]Ea-GANs: Edge-Aware Generative Adversarial Networks for CrossModality MR Image Synthesis
- 9. Ea-GANs: Edge-aware Generative Adversarial Networks for Cross-modality MR Image Synthesis
- 10. CPGAN: Full-Spectrum Content-Parsing Generative Adversarial Networks for Text-to-Image Synthesis
- 更多相關文章...
- • RSS
元素 - RSS 教程 - • ASP.NET Image 控件 - ASP.NET 教程
- • RxJava操作符（六）Utility
- • Flink 數據傳輸及反壓詳解
相關標籤/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
歡迎關注本站公眾號,獲取更多信息
相關文章
- 1. Generative Adversarial Text to Image Synthesis
- 2. [Style Transfer]——Blood Vessel Geometry Synthesis using Generative Adversarial Networks
- 3. Generative Adversarial Networks for Hyperspectral Image Classification
- 4. Binary Generative Adversarial Networks for Image Retrieval
- 5. Bi-Modality Medical Image Synthesis Using Semi-Supervised Sequential Generative Adversarial Networks
- 6. CartoonGAN: Generative Adversarial Networks for Photo Cartoonization
- 7. DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis 論文解讀
- 8. [TMI2019-07]Ea-GANs: Edge-Aware Generative Adversarial Networks for CrossModality MR Image Synthesis
- 9. Ea-GANs: Edge-aware Generative Adversarial Networks for Cross-modality MR Image Synthesis
- 10. CPGAN: Full-Spectrum Content-Parsing Generative Adversarial Networks for Text-to-Image Synthesis