AI Paper Atlas

Research map / Architectures and efficiency / Quantization

Constraint-Aware Deep Neural Network Compression

Changan Chen, Frederick Tung, Naveen Vedula, Greg Mori

ECCV 2018 · Architectures and efficiency › Quantization · approach: Post-training weight quantization · 61 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 a cooling schedule (exponential) to constraint-aware compression instead of unconstrained searchconstraint-aware compression · DTD (60 ms)top-1 accuracy: 56.3 -> 59.0Improved
add exponential cooling instead of one-step compression (ablation)constraint-aware compression · DTD (60 ms)top-1 accuracy: 53.9 ± 6.0% -> 59.0 ± 0.4%Improved
use exponential cooling rather than linear cooling (ablation)constraint-aware compression · DTD (60 ms)top-1 accuracy: 57.8 ± 1.0% -> 59.0 ± 0.4%Improved
add linear cooling instead of one-step compression (ablation)constraint-aware compression · DTD (60 ms)top-1 accuracy: 53.9 ± 6.0% -> 57.8 ± 1.0%Improved
transfer only the final-step hyperparameters from exponential cooling into the one-step baseline (ablation)one-step constraint-aware compression · DTD (60 ms)top-1 accuracy: 59.0 -> 52.6 ± 2.4%Hurt
also transfer the sparsity structure from exponential cooling to the one-step baseline (ablation)one-step constraint-aware compression · DTD (60 ms)top-1 accuracy: 52.6 -> 58.3 ± 1.2%Improved
add one-epoch look-ahead fine-tuning in Bayesian optimization for the one-step baseline (ablation)one-step constraint-aware compression · DTD (60 ms)top-1 accuracy: 53.9% -> 55.9%, std 6.0% -> 1.1%Improved
add constraint-aware compression with exponential cooling instead of unconstrained compressionAlexNet pruning · ImageNet (70 ms)top-1 accuracy: 50.62 -> 53.70Improved
add exponential cooling instead of one-step (ablation)constraint-aware compression · ImageNet (70 ms)top-1 accuracy: 47.27 ± 3.31% -> 53.70 ± 0.15%Improved
constraint-aware compression with latency target of 78.2 ms vs Guided Sparsity LearningAlexNet pruning · ImageNet (GSL comparison)top-1 accuracy: 57.5 -> 57.4No clear effect
constraint-aware compression vs Guided Sparsity Learning at aggressive latency targetsAlexNet pruning · DTD (GSL comparison)top-1 accuracy: 60.9% at 74.2 ms vs 60.1% at 70 ms and 59.0% at 60 msNo clear effect
switch constraint from latency to storage; layers pruned adapt automaticallyconstraint-aware compression · ImageNet (storage 5%)top-1 accuracy: 57.41 -> 54.84% at 232.56 MB -> 11.33 MBNo clear effect

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