AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Choose Your Neuron: Incorporating Domain Knowledge through Neuron-Importance

Ramprasaath R. Selvaraju, Prithvijit Chattopadhyay, Mohamed Elhoseiny, Tilak Sharma, Dhruv Batra, Devi Parikh, Stefan Lee

ECCV 2018 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Generative feature synthesis for zero-shot · 44 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
finetune VGG16 on seen classesNIWT-Attributes · CUB GZSLharmonic mean H: 26.7% -> 37.0%Improved
finetune VGG16 on seen classesNIWT-Attributes · AWA2 GZSLharmonic mean H: 36.1% -> 48.1%Improved
finetune ResNet101 on seen classesNIWT-Attributes · CUB GZSLharmonic mean H: 17.3% -> 27.7%Improved
finetune ResNet101 on seen classesNIWT-Attributes · AWA2 GZSLharmonic mean H: 27.5% -> 40.5%Improved
add L2 regularization toward mean seen weights (ablation)NIWT-Attributes (VGG16) · AWA2 GZSLunseen accuracy: 33.9% -> 41.3%Improved
increase regularization strength beyond 1e-4 (ablation)NIWT-Attributes (VGG16) · AWA2 GZSLunseen accuracyHurt
add regularization (seen accuracy cost) (ablation)NIWT-Attributes (VGG16) · AWA2 GZSLseen accuracy: about 3% lower seen accuracyHurt
extract importance at conv5_3 instead of conv4_3 (ablation)NIWT-Attributes (VGG16) · AWA2 GZSLharmonic mean H: 39.3 -> 48.1Improved
extract importance at conv5_3 instead of fc7 (ablation)NIWT-Attributes (VGG16) · AWA2 GZSLharmonic mean H: 1 -> 48.1Improved
extract importance at conv5_3 instead of fc6 (ablation)NIWT-Attributes (VGG16) · AWA2 GZSLharmonic mean H: 40.2 -> 48.1Improved
use ImageNet images instead of random normal noise for weight optimization (ablation)NIWT-Attributes (VGG16) · CUB GZSLharmonic mean H: 30.2 -> 37.0Improved
use seen-class images instead of ImageNet images (ablation)NIWT-Attributes (VGG16) · CUB GZSLharmonic mean H: 37.0 -> 38.1Improved

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