AI Paper Study
- 일시: 매주 화요일 20:00
- 내용: 논문 리뷰( + Code Reimplemenation / Code Review / Result Reproduction )
- 목적: 지식 확장 및 논문 구현
@hyoseok1223 : Generative Model / Neural Rendering / Computational Photography
@omocomo : Computer Vision / Generative Model / Multi-Modal Learning
@Dongwoo-Im : Computer Vision / Generative Model
| Date | Paper | Topic | Reviewer | Review link |
|---|---|---|---|---|
| 2022.09.08 | Style Transformer: Style Transformer for Image Inversion and Editing | GAN Inversion | @hyoseok1223 @Dongwoo-Im @omocomo |
Link Link |
| 2022.09.13 | ViT: An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale | Transformer, Vision | @Dongwoo-Im | Link |
| 2022.09.13 | Making Convolutional Networks Shift-Invariant Again | Anti-Aliasing | @hyoseok1223 | Link |
| 2022.09.20 | SwinIR: Image Restoration Using Swin Transformer | Image Restoration | @omocomo | Link |
| 2022.09.20 | PoE-GAN: Multimodal Conditional Image Synthesis with Product-of-Experts GANs | Multi-Modal, GAN | @hyoseok1223 | Link |
| 2022.09.27 | SWA: Averaging Weights Leads to Wider Optima and Better Generalization | Optimization | @Dongwoo-Im | Link |
| 2022.10.12 | DeiT: Training data-efficient image transformers & distillation through attention | Efficient Transformer | @hyoseok1223 | Link |
| 2022.11.01 | MLP-Mixer: An all-MLP Architecture for Vision | MLP-like, Vision | @Dongwoo-Im | Link |
| 2022.11.01 | DETR: End-to-End Object Detection with Transformers | Transformer, Object Detection | @hyoseok1223 | Link |
| 2022.11.01 | PoolFormer: MetaFormer Is Actually What You Need for Vision | Transformer, Vision | @omocomo | Link |
| 2022.11.08 | NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis | Graphics, Vision | @hyoseok1223 | Link |
| 2022.11.08 | SimCLR: A Simple Framework for Contrastive Learning of Visual Representations | Self-supervised Learning, Contrastive Learning | @Dongwoo-Im | Link |
| 2022.11.18 | pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D | Graphics, Vision, GAN | @hyoseok1223 | Link |
| 2022.12.20 | DINO: Emerging Properties in Self-Supervised Vision Transformers | Self-supervised Learning | @Dongwoo-Im | Link |
| 2022.12.27 | StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation | GAN Inversion | @hyoseok1223 | Link |
| 2022.12.27 | SwAV: Unsupervised Learning of Visual Features by Contrasting Cluster Assignments | Self-supervised Learning | @Dongwoo-Im | Link |
| 2023.01.31 | EsViT: Efficient self-supervised Vision Transformers | Self-supervised Learning | @Dongwoo-Im | Link |
| 2023.02.06 | Hardware-in-the-loop End-to-end Optimization of Camera Image Processing Pipelines | Hardware Optimization, Computational Photography | @hyoseok1223 | Link |
| 2023.02.06 | SDMP: A Simple Data Mixing Prior for Improving Self-Supervised Learning | Data Mixing Augmentation, Self-supervised Learning | @Dongwoo-Im | Link |
| 2023.02.14 | Time Lens: Event-based Video Frame Interpolation | Video Frame Interpolation, Computational Photography | @hyoseok1223 | Link |
| 2023.02.14 | Revisiting a kNN-based Image Classification System | Knowledge Retrieval, Continual Learning | @Dongwoo-Im | Link |
| 2023.03.07 | MAE: Masked Autoencoders Are Scalable Vision Learners | Self-supervised Learning, Masked Image Modeling | @Dongwoo-Im | Link |
| 2023.03.21 | data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language | Self-supervised Learning, Masked Prediction Task, Multi-modality | @Dongwoo-Im | Link |
| 2023.03.21 | VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolution | INR, Video Interpolation, Video Super-Resolution | @hyoseok1223 | Link |
| 2023.04.06 | CLIP: Learning Transferable Visual Models From Natural Language Supervision | Contrastive Learning, Multi-modality, Zero-shot | @Dongwoo-Im | |
| 2023.04.06 | Neural nano-optics for high-quality thin lens imaging | Computational Imaging, LensLess Imaging | @hyoseok1223 | Link |
| 2023.04.20 | AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition | Visual Adapter, Efficinet Finetuning | @Dongwoo-Im | Link |
| 2023.04.20 | DDPM: Denoising Diffusion Probabilistic Model | Diffusion Model | @hyoseok1223 | Link |
| 2023.04.24 | Barlow Twins: Self-Supervised Learning via Redundancy Reduction | Self-supervised Learning | @Dongwoo-Im | Link |
| 2023.05.01 | VAE: Auto-Encoding Variational Bayes | VAE, Variational Bayes | @Dongwoo-Im | |
| 2023.05.08 | VQ-VAE: Neural Discrete Representation Learning | VQ-VAE, Discrete Latent | @Dongwoo-Im | Link |