AI Paper Atlas

Research map / Architectures and efficiency / Quantization

Accurate Zero-shot Quantization via Hierarchical Teacher-Assistant Distillation

Wonjin Cho, Jeongin Yun, U Kang

ECCV 2026 · Architectures and efficiency › Quantization · approach: Post-training weight quantization · 0 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 intermediate-precision teacher assistant (ablation)Zest · ImageNet-1K val, ResNet-18 W4A4top-1 accuracy: 70.23 -> 70.50Improved
add TA-based image refinement (ablation)Zest · ImageNet-1K val, ResNet-18 W4A4top-1 accuracy: 69.94 -> 70.50Improved
use block-wise instead of end-to-end reconstruction (ablation)Zest · ImageNet-1K val, ResNet-18 W4A4top-1 accuracy: 69.99 -> 70.50Improved
use W8A8 TA instead of W16A16 TA (ablation)Zest · ImageNet-1K val, ResNet-18 W4A4top-1 accuracy: 69.15 -> 70.50Improved
use W8A8 TA instead of W6A6 TA (ablation)Zest · ImageNet-1K val, ResNet-18 W4A4top-1 accuracy: 70.34 -> 70.50Improved
TA equal to student precision (W4A4) instead of W8A8 (ablation)Zest · ImageNet-1K val, ResNet-18 W4A4top-1 accuracy: 70.50 -> 69.19Hurt
hierarchical TA distillation vs best baselines at W4A4Zest · ImageNet-1K ResNet-50 W4A4top-1 accuracy: 75.59 -> 76.32 (Genie)Improved
hierarchical TA distillation vs GenQ at W3A3Zest · ImageNet-1K MobileNetV2 W3A3top-1 accuracy: 59.15 -> 67.74 (GenQ)Improved
hierarchical TA distillation vs GenQ at W3A3Zest · ImageNet-1K ResNet-18 W3A3top-1 accuracy: 68.18 -> 68.45 (GenQ)Improved
increase number of TAs beyond one (ablation)Zest · ImageNet-1K val, ResNet-18 W4A4top-1 accuracyHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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