2023 |
arXiv |
ControlNet : Adding Conditional Control to Text-to-Image Diffusion Models |
김현일 |
Paper, Summary, PPT |
2022 |
arXiv |
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time |
김현일 |
Paper, Summary, PPT |
2022 |
CVPR |
ISDNet: Integrating Shallow and Deep Networks for Efficient Ultra-high Resolution Segmentation |
김현일 |
Paper, Summary, Code, PPT |
2022 |
arXiv |
Instant Neural Graphics Primitives with a Multiresolution Hash Encoding |
김현일 |
Paper, Summary, ppt |
2022 |
arXiv |
EfficientFormer : Vision Transformers at MobileNet Speed |
김현일 |
Paper, Summary, ppt |
2022 |
arxiv |
Hydra Attention: Efficient Attention with Many Heads |
김현일 |
Paper, Summary |
2021 |
arXiv |
Masked-attention Mask Transformer for Universal Image Segmentation |
김현일 |
Paper, Summary |
2021 |
nips |
Per-Pixel Classification is Not All You Need for Semantic Segmentation |
김현일 |
Paper, Summary |
2021 |
arXiv |
A Survey of Visual Transformers |
김현일 |
Paper, Summary, ppt |
2021 |
CVPR |
Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers |
김현일 |
Paper, Summary |
2021 |
ICCV (Spotlight) |
LAMBDANETWORKS: MODELING LONG-RANGE INTERACTIONS WITHOUT ATTENTION |
김현일 |
Paper, Summary |
2021 |
arXiv |
MOBILEVIT: LIGHT-WEIGHT, GENERAL-PURPOSE, AND MOBILE-FRIENDLY VISION TRANSFORMER |
김현일 |
Paper, Summary |
2021 |
arXiv |
ResNet strikes back: An improved training procedure in timm |
김현일 |
Paper, Summary |
2020 |
ECCV |
NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis |
김현일 |
Paper, Summary, ppt |