Name
Abstract | ||
|---|---|---|
In many applications requiring multiple inputs to obtain a desired output, if any of the input data is missing, it often introduces large amounts of bias. Although many techniques have been developed for imputing missing data, the image imputation is still difficult due to complicated nature of natural images. To address this problem, here we proposed a novel framework for missing image data imputation, called Collaborative Generative Adversarial Network (CollaGAN). CollaGAN convert the image imputation problem to a multi-domain images-to-image translation task so that a single generator and discriminator network can successfully estimate the missing data using the remaining clean data set. We demonstrate that CollaGAN produces the images with a higher visual quality compared to the existing competing approaches in various image imputation tasks. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1109/CVPR.2019.00259 | 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) |
Field | DocType | Volume |
Discriminator,Generative adversarial network,Computer science,Artificial intelligence,Imputation (statistics),Missing data,Machine learning | Journal | abs/1901.09764 |
ISSN | Citations | PageRank |
1063-6919 | 2 | 0.38 |
References | Authors | |
16 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Dongwook Lee | 1 | 38 | 3.22 |
| JunYoung Kim | 2 | 3 | 4.80 |
| Won-Jin Moon | 3 | 5 | 2.49 |
| Jong Chul Ye | 4 | 715 | 79.99 |