Research map / Label-efficient and robust learning / Self-supervised and contrastive
Context Autoencoder for Self-supervised Representation Learning
Xiaokang Chen, Mingyu Ding, Xiaodi Wang, Ying Xin, Shentong Mo, Yunhao Wang, Shumin Han, Ping Luo, Gang Zeng, Jingdong Wang
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add decoder and alignment constraint (ablation) | CAE ViT-B 300 ep · ImageNet-1K attentive probing | top-1 accuracy: 71.2 -> 73.8 | Improved |
| add alignment on top of decoder (ablation) | CAE ViT-B 300 ep · ImageNet-1K attentive probing | top-1 accuracy: 72.7 -> 73.8 | Improved |
| add decoder on top of alignment (ablation) | CAE ViT-B 300 ep · ImageNet-1K attentive probing | top-1 accuracy: 71.5 -> 73.8 | Improved |
| add decoder and alignment (ablation) | CAE ViT-B 300 ep · ADE20K | mIoU: 47.0 -> 48.3 | Improved |
| use 50% instead of 40% mask ratio (ablation) | CAE ViT-B 300 ep · ADE20K | mIoU: 47.2 -> 48.3 | Improved |
| raise mask ratio from 50% to 60% (ablation) | CAE ViT-B 300 ep · ImageNet-1K linear probing / ADE20K | accuracy / mIoU: 64.1 -> 64.8 (LIN), 48.3 -> 48.1 (ADE) | Mixed |
| use 4 layers instead of 1 in regressor and decoder (ablation) | CAE · ImageNet-1K attentive probing | top-1 accuracy: 67.5 -> 73.8 | Improved |
| use 5 layers instead of 4 in regressor and decoder (ablation) | CAE · ImageNet-1K attentive probing | top-1 accuracy: 73.8 -> 73.7 | No clear effect |
| set loss tradeoff lambda to 2 instead of 1 (ablation) | CAE · ImageNet-1K linear probing | top-1 accuracy: 63.4 -> 64.1 | Improved |
| use RGB pixel targets instead of DALL-E tokenizer (ablation) | CAE ViT-B 1600 ep · ADE20K | mIoU: 50.2 -> 50.4 | No clear effect |
| use d-VAE tokenizer (ImageNet-1K) instead of DALL-E tokenizer (ablation) | CAE ViT-B 1600 ep · ADE20K | mIoU: 50.2 -> 50.1 | No clear effect |
| pretrain 1600 instead of 300 epochs | CAE ViT-B · ADE20K | mIoU: 48.3 -> 50.2 | Improved |
Closest papers by meaning
- Self-Guided Masked Autoencoder (NeurIPS 2024 · similarity 0.91)
- Exploring Target Representations for Masked Autoencoders (ICLR 2024 · similarity 0.90)
- Understanding and Enhancing Mask-Based Pretraining towards Universal Representations (NeurIPS 2025 · similarity 0.89)
- R-MAE: Regions Meet Masked Autoencoders (ICLR 2024 · similarity 0.88)
- Extending Video Masked Autoencoders to 128 frames (NeurIPS 2024 · similarity 0.88)
- Self-Guided Masked Autoencoders for Domain-Agnostic Self-Supervised Learning (ICLR 2024 · similarity 0.88)
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.
