AI Paper Atlas

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

Interpretable Image Recognition by Constructing Transparent Embedding Space

Jiaqi Wang, Huafeng Liu, Xinyue Wang, Liping Jing

ICCV 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Self-explaining and visual explanation networks · 135 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 orthonormality loss Lorth to Lid+Lcs (ablation)TesNet VGG16/VGG19/ResNet34/DenseNet121/DenseNet161 · CUB-200-2011 (cropped, augmented)accuracy (%): VGG16 79.2 -> 79.4; VGG19 79.8 -> 80.3; ResNet34 80.7 -> 81.1; Dense121 83.4 -> 84.1; Dense161 82.6 -> 83.0Improved
add orthonormality loss Lorth to Lid+Lcs (ablation)TesNet ResNet152 · CUB-200-2011 (cropped, augmented)accuracy (%): 81.6 -> 80.3Hurt
add subspace separation loss Lss to Lid+Lcs+Lorth (ablation)TesNet VGG16 · CUB-200-2011 (cropped, augmented)accuracy (%): 79.4 -> 81.3Improved
add subspace separation loss Lss to Lid+Lcs+Lorth (ablation)TesNet ResNet152 · CUB-200-2011 (cropped, augmented)accuracy (%): 80.3 -> 82.7Improved
add subspace separation loss Lss to Lid+Lcs+Lorth (ablation)TesNet DenseNet121 · CUB-200-2011 (cropped, augmented)accuracy (%): 84.1 -> 84.8Improved
add subspace separation loss Lss to Lid+Lcs+Lorth (ablation)TesNet ResNet34 · CUB-200-2011 (cropped, augmented)accuracy (%): 81.1 -> 82.8Improved
replace ProtoPNet with TesNetProtoPNet VGG16 · CUB-200-2011 (cropped, augmented)accuracy (%): 77.2 -> 81.3Improved
replace ProtoPNet with TesNetProtoPNet DenseNet121 · CUB-200-2011 (cropped, augmented)accuracy (%): 79.0 -> 84.8Improved
switch from non-interpretable baseline to TesNetVGG16 · CUB-200-2011 (cropped, augmented)accuracy (%): 73.3 -> 81.3Improved
switch from non-interpretable baseline to TesNetResNet152 · Stanford Cars (cropped, augmented)accuracy (%): 92.8 -> 92.0Hurt
switch from non-interpretable baseline to TesNetResNet34 · Stanford Cars (cropped, augmented)accuracy (%): 92.6 -> 90.9Hurt
replace ProtoPNet with TesNetProtoPNet ResNet34 · Stanford Cars (cropped, augmented)accuracy (%): 88.8 -> 90.9Improved

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