AI Paper Atlas

Research map / Continual learning / Online and replay-based

Piggyback GAN: Efficient Lifelong Learning for Image Conditioned Generation

Mengyao Zhai, Lei Chen, Jiawei He, Megha Nawhal, Frederick Tung, Greg Mori

ECCV 2020 · Continual learning › Online and replay-based · approach: Gradient projection and plasticity preservation · 29 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
add unconstrained filters (lambda=1/4) to pure factorization (ablation)Piggyback GAN · Paired Task 2 maps->aerialFID: 303.90 -> 171.04Improved
add unconstrained filters (lambda=1/4) to pure factorization (ablation)Piggyback GAN · Paired Task 2 maps->aerialAcc: 99.82 -> 97.99No clear effect
add piggyback filters reusing previous filters, versus a model of one quarter size trained alone (ablation)Piggyback GAN · Paired Task 2 maps->aerialFID: 285.71 -> 171.04Improved
increase the unconstrained filter proportion lambda (ablation)Piggyback GAN · Paired image-conditioned tasksFIDImproved
change the initial task T1 (segmentations->facades instead of semantic labels->street photos) (ablation)Piggyback GAN · Paired Task 2 maps->aerialFID: 171.04 -> 174.67No clear effect
change the initial task T1 (edges->handbags instead of semantic labels->street photos) (ablation)Piggyback GAN · Paired Task 2 maps->aerialFID: 171.04 -> 166.20No clear effect
use Piggyback GAN instead of sequential fine-tuningcontinual paired generation · Paired 4 tasksFID: 259.76 -> 137.87Improved
use Piggyback GAN instead of binary-mask piggybackcontinual paired generation · Paired 4 tasksFID: 178.16 -> 137.87Improved
use Piggyback GAN instead of Lifelong GAN (quality degradation over tasks)continual paired generation · Cityscapes FID over tasksFID: 122.52 -> 160.28 -> 221.07Improved
use Piggyback GAN instead of binary-mask piggybackcontinual unpaired translation · Unpaired 4 translation tasksFID: 149.51 -> 113.89Improved
use Piggyback GAN instead of binary-mask piggybackcontinual style transfer · Unpaired 2 style transfer tasksFID: 118.26 -> 106.95Improved
use Piggyback GAN instead of sequential fine-tuningcontinual style transfer · Unpaired 2 style transfer tasksAcc: 50.00 -> 77.97Improved

Later papers that compared with this method

2 later accepted papers report PiggybackGAN as a baseline in their results tables; 2 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