Deformable DETR: Deformable Transformers for End-to-End Object Detection.

Image segmentation on the oxford-iiit pet dataset using CNN's, GNN's and U-Nets

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

Object detection with multi-level representations generated from deep high-resolution representation learning (HRNetV2h). This is an official implementation for our TPAMI paper "Deep High-Resolutio…

Code release for "Detecting Twenty-thousand Classes using Image-level Supervision".

Code release for "Masked-attention Mask Transformer for Universal Image Segmentation"

[CVPR'23] A Generalized Framework for Video Instance Segmentation