Research map / Label-efficient and robust learning / Self-supervised and contrastive
Semantic-Aware Auto-Encoders for Self-Supervised Representation Learning
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| replace self-reconstruction with cross-view image generation (ablation) | Semantic-Aware AE · ImageNet val | top-1 accuracy: 6.1 -> 46.4 | Helped |
| add semantic alignment using geometric transformation knowledge (ablation) | Semantic-Aware AE · ImageNet | training convergence | Helped |
| add a global pooling feature (ablation) | Semantic-Aware AE · ImageNet | training convergence | Hurt |
| use Semantic-Aware AE rather than BEiT pretraining | ViT-base on COCO 2017 · COCO 2017 val, object detection | APBox: 50.1 -> 51.0 | Helped |
| use Semantic-Aware AE rather than BEiT pretraining | ViT-base on COCO 2017 · COCO 2017 val, instance segmentation | APMask: 43.5 -> 44.1 | Helped |
| use Semantic-Aware AE rather than DINO pretraining | ViT-base on COCO 2017 · COCO 2017 val, object detection | APBox: 50.1 -> 51.0 | Helped |
| use Semantic-Aware AE rather than MAE pretraining | ViT-base on ImageNet fine-tuning · ImageNet | top-1 accuracy: 83.6 -> 83.4 | Hurt |
Closest papers by meaning
- Can Generative Models Improve Self-Supervised Representation Learning? (AAAI 2025 · similarity 0.88)
- Improved Baselines with Representation Autoencoders (NeurIPS 2026 · similarity 0.86)
- A Theoretical Analysis of Self-Supervised Learning for Vision Transformers (ICLR 2025 · similarity 0.86)
- Vision‑Language‑Vision Auto‑Encoder: Scalable Knowledge Distillation from Diffusion Models (NeurIPS 2025 · similarity 0.86)
- Perception Encoder: The best visual embeddings are not at the output of the network (NeurIPS 2025 · similarity 0.86)
- Semantic-Aware Autoregressive Image Modeling for Visual Representation Learning (AAAI 2024 · similarity 0.85)
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.