AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Energy-Constrained Compression for Deep Neural Networks via Weighted Sparse Projection and Layer Input Masking

Haichuan Yang, Yuhao Zhu, Ji Liu

ICLR 2019 · Architectures and efficiency › RNNs and normalization · approach: Differentiable optimization layers · 34 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
Use energy-constrained training with weighted sparse projection and input masking instead of MPAlexNet · ImageNetaccuracy drop: 0.7% -> 0.5%Improved
Use energy-constrained training with weighted sparse projection and input masking instead of MPAlexNet · ImageNetenergy: 34% -> 26%Improved
Use energy-constrained training with weighted sparse projection and input masking instead of EAPSqueezeNet · ImageNetenergy: 76% -> 38%Improved
Use energy-constrained training with weighted sparse projection and input masking instead of SSLMobileNetV2 · ImageNetaccuracy drop: 2.0% -> 1.0%Improved
Use energy-constrained training instead of NetAdaptLeNet-5 · MNISTaccuracy drop: 0.6% -> 0.5%Improved
Use energy-constrained training instead of SSLMobileNetV2 · MS-Celeb-1Maccuracy drop: 0.7% -> 0.2%Improved
Add knowledge distillation to MP (ablation)MP on AlexNet · ImageNetaccuracy drop: 2.6% -> 0.7%Improved
Add knowledge distillation to SSL (ablation)SSL on AlexNet · ImageNetaccuracy drop: 17.6% -> 2.4%Improved
Add knowledge distillation to MP (ablation)MP on SqueezeNet · ImageNetaccuracy drop: 1.9% -> 1.7%Improved
Add knowledge distillation to SSL (ablation)SSL on SqueezeNet · ImageNetaccuracy drop: 16.0% -> 2.7%Improved
Add knowledge distillation to MP (ablation)MP on MobileNetV2 · ImageNetaccuracy drop: 2.0% -> 1.7%Improved
Add knowledge distillation to SSL (ablation)SSL on MobileNetV2 · ImageNetaccuracy drop: 1.9% -> 2.0%No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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