AI Paper Atlas

Research map / Architectures and efficiency / Quantization

Cluster-Promoting Quantization With Bit-Drop for Minimizing Network Quantization Loss

Jung Hyun Lee, Jihun Yun, Sung Ju Hwang, Eunho Yang

ICCV 2021 · Architectures and efficiency › Quantization · approach: Mixed-precision quantization · 12 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 multi-class STE and probabilistic parametrization (CPQ) in place of RQ (ablation)RQ · CIFAR-10 VGG-7 (W/A 4/4 bit)test error (%): 8.43 -> 7.15Improved
add multi-class STE and probabilistic parametrization (CPQ) in place of RQ (ablation)RQ · MNIST LeNet-5 (W/A 3/3 bit)test error (%): 0.69 -> 0.67Improved
add DropBits to CPQ (ablation)CPQ · CIFAR-10 VGG-7 (W/A 4/4 bit)test error (%): 7.15 -> 6.85Improved
add DropBits to CPQ (ablation)CPQ · MNIST LeNet-5 (W/A 3/3 bit)test error (%): 0.67 -> 0.58Improved
add DropBits to CPQ (ablation)CPQ · CIFAR-10 VGG-7 (W/A 2/2 bit)test error (%): 7.68 -> 7.51Improved
add temperature annealing of the Gumbel-Softmax trick (ablation)RQ · CIFAR-10 VGG-7 (W/A 3/3 bit)test error (%): 9.56 -> 10.78Hurt
replace Gumbel-Softmax backward pass with multi-class STE (ablation)RQ · CIFAR-10 VGG-7 (W/A 3/3 bit)test error (%): 9.56 -> 8.44Improved
replace Gumbel-Softmax forward pass with mode selection plus DropBits (ablation)Gumbel-Softmax + multi-class STE · CIFAR-10 VGG-7 (W/A 3/3 bit)test error (%): 8.44 -> 6.94Improved
learn per-layer bit-width with the DropBits regularizer instead of fixing the same bit-widths from scratch (ablation)CPQ + DropBits · ImageNet ResNet-18 (W/A 3/3 bit)top-1 error (%): 41.01 -> 40.30Improved
learn per-layer bit-width with the DropBits regularizer instead of fixing the same bit-widths from scratch (ablation)CPQ + DropBits · VGG-7 CIFAR-10 (W/A 2/2 bit, lambda variant)test error (%): 9.62 -> 7.55Improved
learn per-layer bit-width with the DropBits regularizer instead of fixing the same bit-widths from scratch (ablation)CPQ + DropBits · MNIST LeNet-5 (W/A 3/3 bit)test error (%): 0.65 -> 0.55Improved
learn heterogeneous bit-widths with regularization instead of uniform quantization (ablation)CPQ + DropBits · VGG-7 CIFAR-10 and ResNet-18 ImageNet (W/A 4/4 bit)test error (%): 6.77 -> 6.65 (VGG-7); 33.20 -> 34.30 (ResNet-18)Mixed

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