AI Paper Atlas

Research map / Continual learning / Online and replay-based

Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask Weights

Arun Mallya, Dillon Davis, Svetlana Lazebnik

ECCV 2018 · Continual learning › Online and replay-based · approach: Gradient projection and plasticity preservation · 679 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
learn binary piggyback masks instead of fine-tuning a separate network per taskVGG-16 · CUBStop-1 error (%): 21.30 -> 20.99Improved
learn binary piggyback masks instead of fine-tuning a separate network per taskVGG-16 · Stanford Carstop-1 error (%): 12.49 -> 11.87Improved
learn piggyback masks instead of PackNetVGG-16 · CUBStop-1 error (%): 22.30 -> 20.99Improved
delay task addition from first to last in PackNetPackNet · CUBStop-1 error (%): 22.30 -> 29.69Hurt
use piggyback masks on deeper backbone instead of individual networksDenseNet-121 · WikiArttop-1 error (%): 23.59 -> 29.56Hurt
initialize backbone from ImageNet instead of Places365 (ablation)Piggyback ResNet-50 · CUBStop-1 error (%): 28.50 -> 18.41Improved
initialize backbone from ImageNet instead of random weights (ablation)Piggyback ResNet-50 · CUBStop-1 error (%): 66.24 -> 18.41Improved
initialize backbone from ImageNet instead of random weights (ablation)Piggyback ResNet-50 · Flowerstop-1 error (%): 71.17 -> 5.23Improved
train task-specific batchnorm parameters (ablation)Piggyback ResNet-50 · WikiArttop-1 error (%): 28.67 -> 25.92Improved
train task-specific batchnorm parameters (ablation)Piggyback DenseNet-121 · WikiArttop-1 error (%): 29.56 -> 25.90Improved
train task-specific batchnorm parameters (ablation)Piggyback ResNet-50 · Sketchtop-1 error (%): 20.09 -> 19.82Improved
initialize mask weights with a constant and use Adam instead of other options (ablation)Piggyback · fine-grained classificationaccuracy: ~2%Improved

Later papers that compared with this method

3 later accepted papers report Piggyback 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