AI Paper Atlas

Research map / Continual learning / Online and replay-based

CAM-GAN: Continual Adaptation Modules for Generative Adversarial Networks

Sakshi Varshney, Vinay Kumar Verma, Srijith P K, Lawrence Carin, Piyush Rai

NeurIPS 2021 · Continual learning › Online and replay-based · approach: Gradient projection and plasticity preservation · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use CAM-GAN instead of GAN-Memorycontinual unconditional generation · CathedralFID: 15.6 -> 9.52Improved
Use CAM-GAN instead of GAN-Memorycontinual unconditional generation · X-RayFID: 17.18 -> 14.24Improved
Use CAM-GAN instead of GAN-Memorycontinual unconditional generation · FlowerFID: 14.8 -> 23.0Hurt
Use CAM-GAN instead of GAN-Memorycontinual unconditional generation · AnimeFID: 13.29 -> 13.1Improved
Initialize adapters from the most similar task using FIM-based task similarity (ablation)CAM-GAN · CatFID: 18.2 -> 16.4Improved
Initialize adapters from the most similar task using FIM-based task similarity (ablation)CAM-GAN · Brain-MRIFID: 15.8 -> 15.0Improved
Initialize adapters from the most similar task using FIM-based task similarity (ablation)CAM-GAN · AnimeFID: 13.3 -> 10.9Improved
Reduce adapter parameter growth to 50% while using task-similarity initialization (ablation)CAM-GAN · CatFID: 16.4 -> 18.8Hurt
Reduce adapter parameter growth to 50% while using task-similarity initialization (ablation)CAM-GAN · Brain-MRIFID: 15.0 -> 15.9Hurt
Reduce adapter parameter growth to 50% while using task-similarity initialization (ablation)CAM-GAN · AnimeFID: 10.9 -> 13.8Hurt
Add the 1x1 groupwise convolution adapter alongside the 3x3 groupwise adapter (ablation)CAM-GAN · Cat and Brain-MRIFIDImproved
Add residual bias in transformed feature space (ablation)CAM-GAN generator training · CelebAtraining stability: 125K iterationsImproved

Later papers that compared with this method

1 later accepted paper reports CAM-GAN as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy