LeapLab
LeapLab
Pseudo-Q
[CVPR 2022] Pseudo-Q: Generating Pseudo Language Queries for Visual Grounding
DAT
Repository of Vision Transformer with Deformable Attention (CVPR2022) and DAT++: Spatially Dynamic Vision Transformerwith Deformable Attention
DAT-Jittor
Jittor implementation of Vision Transformer with Deformable Attention
DAPrompt
Pytorch implementation of DAPrompt: https://arxiv.org/abs/2202.06687
Cross-Modal-Adapter
[arXiv] Cross-Modal Adapter for Text-Video Retrieval
EfficientTrain
1.5−3.0× lossless training or pre-training speedup. An off-the-shelf, easy-to-implement algorithm for the efficient training of foundation visual backbones.
DAT-Segmentation
Repository of Vision Transformer with Deformable Attention (CVPR2022) and DAT++: Spatially Dynamic Vision Transformerwith Deformable Attention