Research map / Architectures and efficiency / Neural architecture search
Masked Distillation Advances Self-Supervised Transformer Architecture Search
Caixia Yan, Xiaojun Chang, Zhihui Li, Lina Yao, Minnan Luo, Qinghua Zheng
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes a masked-distillation-based approach to self-supervised transformer architecture search, so that architectures can be searched without labeled data.
Problem
Transformer architecture search (TAS) typically requires labeled data, which is expensive; the abstract motivates self-supervised TAS for real-world deployment.
Approach
Extends transformer architecture search into the self-supervised setting by using masked distillation to guide the search, removing the need for data labels.
Closest papers by meaning
- AutoFormer: Searching Transformers for Visual Recognition (ICCV 2021 · similarity 0.90)
- GLiT: Neural Architecture Search for Global and Local Image Transformer (ICCV 2021 · similarity 0.89)
- Supervised Masked Knowledge Distillation for Few-Shot Transformers (CVPR 2023 · similarity 0.89)
- Auto-Prox: Training-Free Vision Transformer Architecture Search via Automatic Proxy Discovery (AAAI 2024 · similarity 0.87)
- L-SWAG: Layer-Sample Wise Activation with Gradients Information for Zero-Shot NAS on Vision Transformers (CVPR 2025 · similarity 0.86)
- A Theoretical Analysis of Self-Supervised Learning for Vision Transformers (ICLR 2025 · similarity 0.86)
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.
