AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Brain-Mediated Transfer Learning of Convolutional Neural Networks

Satoshi Nishida, Yusuke Nakano, Antoine Blanc, Naoya Maeda, Masataka Kado, Shinji Nishimoto

AAAI 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 26 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
transform VGG-16 features into brain-response representations with BTL instead of using direct TLScene description estimation · Scene descriptions (Task1)estimation performance: 0.537 -> 0.546Improved
transform CNN features into brain-response representations with BTL instead of direct TLImpression rating estimation · Impression ratings (Task2)estimation performance: 0.501 -> 0.517Improved
use BTL rather than direct TLClick rate estimation · Click rate (Task3-1)estimation performance: 0.510 -> 0.505Mixed
use brain-mediated features rather than direct CNN featuresView completion rate estimation · View completion rate (Task3-2)estimation performance: 0.303 -> 0.444Improved
use BTL rather than direct TLAd preference estimation · Ad preference (Task4)estimation performance: 0.365 -> 0.387Improved
add SoundNet acoustic features (ablation)BTL impression rating estimation · Impression ratings (Task2)estimation performance: 0.500 -> 0.517Improved
add SoundNet acoustic features (ablation)BTL scene description estimation · Scene descriptions (Task1)estimation performance: 0.546 -> 0.536Hurt
add vox2vox (ablation)BTL voxel-response prediction with VGG-16 and SoundNet · Web ad movies test fMRIvoxel-response prediction accuracy: 0.106 -> 0.108Improved
add vox2vox (ablation)BTL impression rating estimation · Impression ratings (Task2)estimation performance: 0.516 -> 0.517Improved
add vox2vox (ablation)BTL click rate estimation with VGG-16 · Click rate (Task3-1)estimation performance: 0.505 -> 0.502Hurt
add vox2vox (ablation)BTL view completion estimation with VGG-16 · View completion rate (Task3-2)estimation performance: 0.440 -> 0.444Improved
add vox2vox (ablation)BTL ad preference estimation with VGG-16 and SoundNet · Ad preference (Task4)estimation performance: 0.381 -> 0.387Improved

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