AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Auto-Transfer: Learning to Route Transferable Representations

Keerthiram Murugesan, Vijay Sadashivaiah, Ronny Luss, Karthikeyan Shanmugam, Pin-Yu Chen, Amit Dhurandhar

ICLR 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Statistical transfer learning · 1 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
route source representations to target layers with Auto-TransferAuto-Transfer vs SAD · CUB200accuracy: 68.29 -> 74.76Improved
route source representations to target layers with Auto-TransferAuto-Transfer vs SAD · Stanford Dogsaccuracy: 76.06 -> 86.16Improved
route source representations to target layers with Auto-TransferAuto-Transfer vs SAD · MIT67accuracy: 66.47 -> 75.86Improved
route source representations to target layers with Auto-TransferAuto-Transfer vs SAD · Stanford40accuracy: 63.08 -> 80.10Improved
use Auto-Transfer rather than L2T-wwCIFAR100 with TinyImageNet source · CIFAR100accuracy: 70.96{$\pm$ 0.61} -> 72.48{$\pm$ 0.42} (full); 70.96{$\pm$ 0.61} -> 70.48{$\pm$ 0.25} (fixed); 70.96{$\pm$ 0.61} -> 70.8Mixed
use Auto-Transfer rather than L2T-wwSTL10 with TinyImageNet source · STL10accuracy: 78.31{$\pm$ 0.21} -> 82.09{$\pm$ 0.29}Improved
use matched-architecture Auto-Transfer instead of finetuningResNet18 source and target · CUB200accuracy: 42.96{$\pm$ 1.45} -> 66.97{$\pm$ 1.38}Improved
use matched-architecture Auto-Transfer instead of finetuningResNet18 source and target · Stanford Dogsaccuracy: 53.02{$\pm$ 3.57} -> 79.46{$\pm$ 1.05}Improved
use matched-architecture Auto-Transfer instead of finetuningResNet18 source and target · MIT67accuracy: 47.93{$\pm$ 3.66} -> 69.54{$\pm$ 2.49}Improved
use matched-architecture Auto-Transfer instead of finetuningResNet18 source and target · Stanford40accuracy: 34.40{$\pm$ 5.94} -> 75.07{$\pm$ 2.55}Improved
fix selected layer pairs rather than using bandit routing during training (ablation)Auto-Transfer · CUB200accuracy: 73.09 -> 75.15Improved
fix selected layer pairs rather than using bandit routing during training (ablation)Auto-Transfer · Stanford Dogsaccuracy: 85.05 -> 86.40Improved

Later papers that compared with this method

1 later accepted paper reports AutoTransfer 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