AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Contrastive Masked Autoencoders are Stronger Vision Learners

Zhicheng Huang, Xiaojie Jin, Cheng-Ze Lu, Qibin Hou, Ming‐Ming Cheng, Dongmei Fu, Xiaohui Shen, Jiashi Feng

TPAMI 2023 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Masked autoencoder pretraining · 234 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 vanilla contrastive learning (random crop) to MAE (ablation)MAE · ImageNet-1k (300 ep, ablation)top-1 accuracy: 82.9 -> 83.1Improved
add pixel shifting augmentation to contrastive MAE (ablation)CMAE · ImageNet-1k (300 ep, ablation)top-1 accuracy: 83.1 -> 83.6Improved
add feature decoder (ablation)CMAE · ImageNet-1k (300 ep, ablation)top-1 accuracy: 83.6 -> 83.8Improved
use pixel shifting instead of random resized crop (ablation)CMAE · ImageNet-1k (300 ep, ablation)top-1 accuracy: 83.0 -> 83.4Improved
add color jittering on the momentum branch (ablation)CMAE · ImageNet-1k (300 ep, ablation)top-1 accuracy: 83.4 -> 83.8Improved
use InfoNCE instead of BYOL-style contrastive loss (ablation)CMAE · ImageNet-1k (300 ep, ablation)top-1 accuracy: 83.4 -> 83.8Improved
add a two-block feature decoder instead of none (ablation)CMAE · ImageNet-1k (300 ep, ablation)top-1 accuracy: 83.6 -> 83.8Improved
share weights between feature decoder and pixel decoder (ablation)CMAE · ImageNet-1k (300 ep, ablation)top-1 accuracy: 83.8 -> 83.4Hurt
increase feature decoder depth from 2 to 4 (ablation)CMAE · ImageNet-1k (300 ep, ablation)top-1 accuracy: 83.8 -> 83.8No clear effect
mask 75% of patches in the momentum branch (ablation)CMAE · ImageNet-1k (300 ep, ablation)top-1 accuracy: 83.8 -> 83.0Hurt
raise contrastive loss weight from 1.0 to 2.0 (ablation)CMAE · ImageNet-1k (300 ep, ablation)top-1 accuracy: 83.8 -> 83.2Hurt
add CMAE contrastive objective to MAE on a conv hybrid ViTConvMAE · ImageNet-1k fine-tuning (hybrid conv ViT-B)top-1 accuracy: 84.6 -> 85.3Improved

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