AI Paper Atlas

Research map / Architectures and efficiency / Quantization

MetaAug: Meta-Data Augmentation for Post-Training Quantization

Cuong Van Pham, Hoang Anh Dung, Cuong Cao Nguyen, Trung Le, Dinh Phung, Gustavo Carneiro, Thanh-Toan Do

ECCV 2024 · Architectures and efficiency › Quantization · approach: Post-training quantization of ViTs · 3 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
train transformation network with validation loss only (no preservation or margin loss) (ablation)MetaAug · ImageNet W2A2top-1 accuracy (%): 53.71 -> 53.45Hurt
add distribution preservation loss L_DP instead of MSE (ablation)MetaAug · ImageNet W2A2top-1 accuracy (%): 53.64 -> 54.09Improved
add margin loss to prevent identity mapping (ablation)MetaAug with L_DP · ImageNet W2A2top-1 accuracy (%): 54.09 -> 54.22Improved
use MetaAug instead of Genie-MGenie PTQ · ImageNet W2A2top-1 accuracy (%): 53.71 -> 54.22Improved
use learned transformation network instead of traditional augmentation (Mixup, Cutmix) (ablation)Genie PTQ calibration data · ImageNet W2A2 ResNet-18top-1 accuracy (%): 54.15 -> 54.22Improved
apply photometric augmentation (brightness, contrast) to calibration data (ablation)Genie-M · ImageNet W2A2 ResNet-18top-1 accuracy (%): 53.71 -> 53.35Hurt
combine MetaAug with Cutmix (ablation)MetaAug · ImageNet W2A2 ResNet-18top-1 accuracy (%): 54.22 -> 54.63Improved
use MetaAug instead of QDrop in reducing train-test gapPTQ · ImageNet W2A2 ResNet-18test accuracy (%): 51.14 -> 54.22Improved
use MetaAug* instead of Bit-Shrinking*PTQ · ImageNet W4A4 ResNet-50top-1 accuracy (%): 76.04 -> 75.78Hurt

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