14 papers
Architectures & Training¶
CNN/Transformer 아키텍처와 학습 기법
📝 리뷰 · ⚡ 짧은 리뷰 · 📒 필기 PDF · 📊 발표 자료 · 📎 기타 자료 · 💻 코드 · 🔗 관련 링크 — 제목을 누르면 원문으로 이동합니다.
| Paper | Venue | Review | Materials |
|---|---|---|---|
| AlexNet: ImageNet Classification with Deep Convolutional Neural Networks | NeurIPS 2012 | 📒 📊 📎 | |
| How transferable are features in deep neural networks? | NeurIPS 2014 | 📒 | |
| VGG: Very Deep Convolutional Networks for Large-Scale Image Recognition | ICLR 2015 | 📊 | |
| Learning to learn by gradient descent by gradient descent | NeurIPS 2016 | 📒 📊 | |
| NAS: Neural Architecture Search with Reinforcement Learning | ICLR 2017 | 📒 📊 | |
| Transformer: Attention Is All You Need | NeurIPS 2017 | 📊 💻 | |
| Mixup: Beyond Empirical Risk Minimization | ICLR 2018 | 📝 ⚡ | |
| ViT: An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale | ICLR 2021 | 📒 📊 | |
| The Forward-Forward Algorithm: Some Preliminary Investigations | arXiv 2022 | 📒 📊 💻 | |
| Rotary Position Embedding for Vision Transformer | ECCV 2024 | 📝 | |
| XDomainMix: Cross-Domain Feature Augmentation for Domain Generalization | IJCAI 2024 | 📝 | 📊 |
| Hyper-Connections | ICLR 2025 | 📝 | |
| mHC: Manifold-Constrained Hyper-Connections | arXiv 2026 | 📝 | 📊 |
| Lipschitz Continuity (작성 중) | 📒 |