DeepDream
ディープドリーム / 2015– / Technique / Digital Art
Google's visualization technique repeatedly amplifies features learned by an image-recognition network, making eyes, animals and towers emerge excessively from clouds, rocks and leaves until misrecognition becomes a recursive hallucinatory surface.
Eyes and animal faces repeated across the frame / Swirling texture multiplying along source contours / Multi-scale repetition that reveals new figures when viewed closer / Saturated blue, yellow and violet rolling continuously
Dictionary entry
- Best used for
- Exhibits and critical images that make machine misrecognition immediately visible · Music video and cover imagery that keeps a source landscape beneath a multi-scale hallucination
- Type
- Add type after processing, keeping it short, bold and simple enough not to fight the detail.
- Composition
- Preserve the source's large composition and amplify related features at several scales to create recursion into depth.
- Material
- Choose layers in a trained vision model and iteratively increase their activation through gradient ascent.
- Caution
- It is not a swirl filter or pasted dog faces. Preserve which layer and feature were amplified and how they bind to the source.
- Further study
- Feature visualization and layer selection / Iterative zoom and octave scales / GoogLeNet ImageNet feature bias
Related entries
Cite this entry
The dictionary is meant to be linked to. Take whichever form fits where you are writing.
- Link
- https://indexstyle.org/styles/deepdream
- Markdown
- [DeepDream — IndexStyle](https://indexstyle.org/styles/deepdream)
- HTML
- <a href="https://indexstyle.org/styles/deepdream">DeepDream — IndexStyle</a>