AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Compositional Explanations of Neurons

Jesse Mu, Jacob Andreas

NeurIPS 2020 · Vision-language and multimodal › Human and embodied modeling · approach: Language-grounded visual concept learning · 64 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
increase max explanation formula length from 1 (NetDissect) to 10 (ablation)neuron explanation search · ResNet-18 Places365mean IoU: 0.059 -> 0.099Improved
increase max formula length beyond 10 (ablation)neuron explanation search · ResNet-18 Places365mean IoUNo clear effect
increase max formula length (up to 30+) (ablation)neuron explanation search · SNLI BiLSTMIoUImproved
neurons with higher explanation IoUResNet-18 · Places365model accuracy when neuron active: r = 0.31Improved
neurons with higher explanation IoUBiLSTM NLI · SNLImodel accuracy when neuron active: r = -0.60Hurt

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