AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Neural Network Encapsulation

Hongyang Li, Xiaoyang Guo, Bo DaiWanli Ouyang, Xiaogang Wang

ECCV 2018 · Architectures and efficiency › Pruning and efficient tuning · approach: Joint pruning and quantization · 53 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
replace master-only capConv with master/aide approximate routing (ablation)EncapNet 6-layer · CIFAR-10 (6-layer)error rate (%): 13.87 -> 11.93Improved
replace dynamic-routing CapNet with EncapNet master/aide (parameters)6-layer network · CIFAR-10 (6-layer)param count (Mb): 151.24 -> 60.68Improved
replace dynamic-routing CapNet with EncapNet master/aide6-layer network · CIFAR-10 (6-layer)error rate (%): 14.28 -> 11.93Improved
replace EM-routing CapNet with EncapNet master/aide6-layer network · MNIST (6-layer)error rate (%): 0.31 -> 0.25Improved
add aide branch (master/aide v3) to master-only capConv (ablation)EncapNet-18 · CIFAR-10 (18-layer ablation, capConv design)error rate (%): 9.83 -> 7.41Improved
add skip connections on both types to master/aide v3 (ablation)EncapNet-18 · CIFAR-10 (18-layer ablation, capConv design)error rate (%): 7.41 -> 5.82Improved
add a second OT divergence to each module (ablation)EncapNet-18 · CIFAR-10 (18-layer ablation, capConv design)error rate (%): 5.82 -> 4.55Improved
add OT (Sinkhorn) feedback loss instead of KL loss (ablation)EncapNet-18 · CIFAR-10 (18-layer ablation, regularization)error rate (%): 5.31 -> 4.58Improved
add OT feedback loss to ResNet-18 (ablation)ResNet-18 · CIFAR-10 (18-layer ablation, regularization)error rate (%): 8.03 -> 7.67Improved
add bias fix to Sinkhorn divergence (ablation)EncapNet-18 OT loss · CIFAR-10 (18-layer ablation, regularization)error rate (%): 4.71 -> 4.58Improved
add feature extractor f_psi before comparing inputs (ablation)EncapNet-18 OT loss · CIFAR-10 (18-layer ablation, regularization)error rate (%): 5.79 -> 4.58Improved
use capsule generator instead of vanilla CNN generator g_phi (ablation)EncapNet-18 OT loss · CIFAR-10 (18-layer ablation, regularization)error rate (%): 5.01 -> 4.58Improved

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