AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Interpreting Deep Neural Networks with Relative Sectional Propagation by Analyzing Comparative Gradients and Hostile Activations

AAAI 2021 · Architectures and efficiency › RNNs and normalization · approach: Representation geometry and collapse · 16 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Apply RSP instead of other fully decomposed attribution methodsVGG-16 · PASCAL VOC 2007, predicted classesPointing Game: RSP .946; c*RSP .881Mixed
Use contrastive initialization for the relative gradient map (ablation)RSP on PASCAL VOC 2007 · PASCAL VOC 2007, predicted classesPointing Game: .946 -> .881Hurt
Use contrastive initialization for the relative gradient map (ablation)RSP on PASCAL VOC 2007 · PASCAL VOC 2007, predicted classesPointing Game: .909 -> .949Helped
Use contrastive initialization for the relative gradient map (ablation)RSP on COCO 2014 · COCO 2014 validation, predicted classesPointing Game: .725 -> .675; .688 -> .697Mixed
Add CRF refinement to RSPRSP · ImageNet SegmentationmIoU: 60.81 -> 64.51Helped

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