[ICCV2019] Detecting the Unexpected via Image Resynthesis
作者：Krzysztof Lis ， EPFL Introduction 利用GAN網絡做圖像中未知物體的 anomaly detection。該任務簡單來說即爲，訓練數據中沒有該類別物體以及其標籤，但測試數據中有，如何定位該物體。傳統思路有兩種：1、根據預測的分割圖中較低的confidence score來找未知物體的區域（segmentation uncertainty）；2、利用auto-e
相關文章
- 1. [ICCV2019] Learning Fixed Points in Generative Adversarial Networks: From Image-to-Image Translation
- 2. Few-shot Object Detection via Feature Reweighting (ICCV2019)
- 3. Detecting Deceptive Review Spam via Attention-Based Neural Networks
- 4. [ICCV2019] InGAN: Capturing and Remapping the 「DNA」 of a Natural Image
- 5. ICCV2019-ERL-Net：Entangled Representation Learning for Single Image De-Raining
- 6. CFSNet: Toward a Controllable Feature Space for Image Restoration ICCV2019
- 7. [ICCV2019] Unsupervised Robust Disentangling of Latent Characteristics for Image Synthesis
- 8. Image Denoising via CNNs: An Adversarial Approach
- 9. 《GCAMatting：Natural Image Matting via Guided Contextual Attention》
- 10. The usage of docker image wurstmeister/kafka
- 更多相關文章...
- • RSS
元素 - RSS 教程 - • ASP.NET Image 控件 - ASP.NET 教程
- • Docker 清理命令
- • Docker容器實戰(七) - 容器眼光下的文件系統
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。
最新文章
歡迎關注本站公眾號,獲取更多信息
相關文章
- 1. [ICCV2019] Learning Fixed Points in Generative Adversarial Networks: From Image-to-Image Translation
- 2. Few-shot Object Detection via Feature Reweighting (ICCV2019)
- 3. Detecting Deceptive Review Spam via Attention-Based Neural Networks
- 4. [ICCV2019] InGAN: Capturing and Remapping the 「DNA」 of a Natural Image
- 5. ICCV2019-ERL-Net：Entangled Representation Learning for Single Image De-Raining
- 6. CFSNet: Toward a Controllable Feature Space for Image Restoration ICCV2019
- 7. [ICCV2019] Unsupervised Robust Disentangling of Latent Characteristics for Image Synthesis
- 8. Image Denoising via CNNs: An Adversarial Approach
- 9. 《GCAMatting：Natural Image Matting via Guided Contextual Attention》
- 10. The usage of docker image wurstmeister/kafka