AI Paper Atlas

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

Learning What and Where to Transfer

Yunhun Jang, Hankook Lee, Sung Ju Hwang, Jinwoo Shin

ICML 2019 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Statistical transfer learning · 24 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 sample-conditioned channel and layer-transfer weights jointlyL2T-ww · CUB200, MIT67, Stanford40, Stanford Dogsaccuracy: 58.90 ± 1.32 -> 65.05 ± 1.19 (CUB200); 61.42 ± 1.68 -> 64.85 ± 2.75 (MIT67); 60.20 ± 1.34 -> 63.08 ± 0.88 (Stanford40); Improved
learn sample-conditioned channel importance rather than using unweighted feature matchingL2T-w · CUB200, MIT67, Stanford40accuracy: 47.60 ± 0.31 -> 51.95 ± 0.83 (CUB200); 55.15 ± 0.93 -> 60.41 ± 0.37 (MIT67); 42.93 ± 1.48 -> 46.25 ± 3.66 (Stanford40)Improved
learn layer associations over all candidate pairs instead of using hand-crafted one-to-one matchingL2T-ww · CIFAR-100, STL-10, CUB200, MIT67, Stanford40, Stanford Dogsaccuracy: 70.02 ± 0.19 -> 70.96 ± 0.61 (CIFAR-100); 76.42 ± 0.52 -> 78.31 ± 0.21 (STL-10); 56.61 ± 0.20 -> 65.05 ± 1.19 (CUB200); Improved
use meta-networks to produce sample-specific transfer weights instead of constant meta-weights (ablation)L2T-ww · CUB200accuracy: 61.75 -> 65.05Improved
use meta-networks to produce sample-specific transfer weights instead of constant meta-weights (ablation)L2T-ww · MIT67accuracy: 64.10 -> 64.85Improved
use meta-networks to produce sample-specific transfer weights instead of constant meta-weights (ablation)L2T-ww · Stanford40accuracy: 58.88 -> 63.08Improved
use the proposed three-stage bilevel scheme instead of the original scheme (ablation)L2T-ww · CUB200accuracy: 35.38 -> 65.05Improved
use the proposed three-stage bilevel scheme instead of the original scheme (ablation)L2T-ww · MIT67accuracy: 54.18 -> 64.85Improved
use the proposed three-stage bilevel scheme instead of the original scheme (ablation)L2T-ww · Stanford40accuracy: 53.47 -> 63.08Improved
transfer from TinyImageNet and CIFAR-10 sources simultaneously instead of TinyImageNet aloneL2T-ww · STL-10accuracy: 78.31 ± 0.21 -> 80.52 ± 0.29Improved
reduce the target training set to 50 samples per class while using L2T-ww rather than the strongest listed baselineL2T-ww · CIFAR-10, 50 samples per classaccuracy: 53.76% -> 64.91%Improved

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