[rework] rework w/ paper list

kozistr / Awesome-GANs

Awesome Generative Adversarial Networks with tensorflow

MIT License

761 stars 163 forks source link

[rework] rework w/ paper list #15

Open kozistr opened 4 years ago

kozistr commented 4 years ago

Select some of the papers which have impacts and important as i think,
Summary all of the papers within 3 lines!
Grouping the papers w/ following characteristic

DonaldTsang commented 4 years ago

Agreed, but the problem is that more and more papers are coming out, especially with the recorrection with https://github.com/nightrome/really-awesome-gan Is it possible to judge a paper based on the amount of times it get referenced by other papers (assume metrics by SemanticScholar and ResearchGate)?

kozistr commented 4 years ago

Agreed, but the problem is that more and more papers are coming out, especially with the recorrection with https://github.com/nightrome/really-awesome-gan Is it possible to judge a paper based on the amount of times it get referenced by other papers (assume metrics by SemanticScholar and ResearchGate)?

reference count usually is a good metric for judging the paper, but in case of purpose of this repo, is not as i think! so, not recommending all of GAN papers, but the paper what i and others think it is good to read ( based on my and others experiences).

DonaldTsang commented 4 years ago

In that case, besides popularity, there should be a "uniqueness" factor, since many GANs can be abstracted away to having the same meta-structure. See https://github.com/kozistr/Awesome-GANs/issues/18 for some examples. Of course I would hope that more varieties of meta-structures would lead to more innovation, but then again that is just hope if implementing all GANs are impossible.