5,321
edits
Generative adversarial network: Difference between revisions
Generative adversarial network (view source)
Revision as of 18:56, 15 January 2020
, 15 January 2020→Important Papers
No edit summary |
|||
| Line 59: | Line 59: | ||
** Basically, each "unit" or channel of the intermediate representations correspond to some features like windows or trees | ** Basically, each "unit" or channel of the intermediate representations correspond to some features like windows or trees | ||
** Dissection: Identifying which units correspond to features can be done by visualizing each channel as a heatmap. Then threshold the heatmap so each value is binary 0/1. Calculate the IOU between the heatmap and the segmented feature in the generated picture. | ** Dissection: Identifying which units correspond to features can be done by visualizing each channel as a heatmap. Then threshold the heatmap so each value is binary 0/1. Calculate the IOU between the heatmap and the segmented feature in the generated picture. | ||
** Intervention: By zeroing out channels, you can remove windows or trees from the generated image. Alternatively you can add windows or trees at specific locations by activating the neurons at that location. | ** Intervention: By zeroing out channels, you can remove windows or trees from the generated image. Alternatively you can add windows or trees at specific locations by activating the neurons at that location of the corresponding window/tree channel. | ||
** This is fairly specific to CNN architectures where there is a locality correspondence between the intermediate representations and the output image. | ** This is fairly specific to CNN architectures where there is a locality correspondence between the intermediate representations and the output image. | ||
==Resources== | ==Resources== | ||
* [https://github.com/soumith/ganhacks Tricks for Training GANs] | * [https://github.com/soumith/ganhacks Tricks for Training GANs] | ||