L
Lewei Lu
Researcher at Microsoft
Publications - 21
Citations - 3141
Lewei Lu is an academic researcher from Microsoft. The author has contributed to research in topics: Computer science & Inpainting. The author has an hindex of 5, co-authored 8 publications receiving 883 citations.
Papers
More filters
Posted Content
Deformable DETR: Deformable Transformers for End-to-End Object Detection
TL;DR: Deformable DETR, whose attention modules only attend to a small set of key sampling points around a reference, can achieve better performance than DETR (especially on small objects) with 10$\times less training epochs.
Posted Content
VL-BERT: Pre-training of Generic Visual-Linguistic Representations
TL;DR: A new pre-trainable generic representation for visual-linguistic tasks, called Visual-Linguistic BERT (VL-BERT), which adopts the simple yet powerful Transformer model as the backbone, and extends it to take both visual and linguistic embedded features as input.
Proceedings Article
VL-BERT: Pre-training of Generic Visual-Linguistic Representations
TL;DR: In this paper, a new pre-trainable generic representation for visual-linguistic tasks, called Visual-Linguistic BERT (VL-BERT for short), is introduced.
Proceedings Article
Deformable DETR: Deformable Transformers for End-to-End Object Detection
TL;DR: Deformable DETR as discussed by the authors proposes to only attend to a small set of key sampling points around a reference, which can achieve better performance than DETR with 10× less training epochs.
Journal ArticleDOI
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
Wenhai Wang,Jifeng Dai,Zhe Chen,Zhenhang Huang,Zhiqi Li,Xizhou Zhu,Xiao-hua Hu,Tong Lu,Lewei Lu,Hongsheng Li,Xiaogang Wang,Yu Qiao +11 more
TL;DR: In this paper , a new large-scale CNN-based foundation model, termed InternImage, is presented, which can obtain the gain from increasing parameters and training data like ViTs.