AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Interpretable CNNs for Object Classification

Quanshi Zhang, Xin Wang, Ying Nian Wu, Huilin Zhou, Song Chun Zhu

TPAMI 2020 · Architectures and efficiency › CNN design · approach: Filter design and trained-filter analysis · 79 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
add interpretable conv-layer with filter lossVGG-16 · VOC Part (binary)part interpretability: 0.495 -> 0.770Improved
add interpretable conv-layer with filter lossVGG-S · VOC Part (binary)part interpretability: 0.257 -> 0.390Improved
add interpretable conv-layer with filter lossVGG-16 · ILSVRC DET Animal-Part (binary)location instability: 0.144 -> 0.085Improved
add interpretable layer vs adding an ordinary conv-layerVGG-16 · ILSVRC DET Animal-Part (binary)location instability: 0.121 -> 0.085Improved
add filter loss (vs mask layer alone) (ablation)VGG-16 · VOC Part (binary)semantic purity: 0.370 -> 0.566Improved
add filter loss (vs mask layer alone) (ablation)VGG-M · VOC Part (binary)semantic purity: 0.253 -> 0.465Improved
add filter loss (vs mask layer alone) (ablation)VGG-16 · VOC Part (binary)location instability (first conv-layer): 0.134 -> 0.126Improved
add filter loss to interpretable CNN (ablation)VGG-16 · VOC Part (binary)location instability: 0.094 -> 0.096No clear effect
add filter loss to interpretable CNN (ablation)VGG-16 · VOC Part (binary)classification accuracy: 97.02 -> 95.39Hurt
use interpretable CNN instead of ordinary CNNVGG-16 · VOC Part (binary)classification accuracy: 98.66 -> 95.39Hurt
use interpretable CNN instead of ordinary CNNVGG-M · VOC Part (multi-category, softmax)classification accuracy: 81.93 -> 88.03Improved
use interpretable CNN instead of ordinary CNNVGG-16 · VOC Part (multi-category, softmax)classification accuracy: 89.71 -> 91.60Improved

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