Cars. Music. Travel. Developing algorithms for efficient large-scale training and inference.
pytorch-vit. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
309setr-pytorch. Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers
201pytorch-frn. Filter Response Normalization Layer in PyTorch
121DeepEvent-VO. Fusing Event Frame Streams in DeepVO
5deep-prediction. Deep Prediction for Self-Driving Cars
4Constrained-BA. Constrained Bundle Adjustment for Reliable 3D Reconstruction
3