#COCO

Logo of ssd.pytorch
ssd.pytorch
This PyTorch-based implementation of the Single Shot MultiBox Detector offers a streamlined approach for efficient object detection. Compatible with popular datasets and offering straightforward processes for setup, training, and evaluation, this project supports NVIDIA GPU acceleration and real-time training performance enhancements via Visdom integration. Users can explore transfer learning with pre-trained model weights, supported by comprehensive instructions for both command-line and Jupyter notebook demos. Regular updates aim to expand capabilities, including support for SSD512 and custom dataset training.
Logo of MIMDet
MIMDet
Utilizing Masked Image Modeling with a Vanilla ViT, this project enhances object detection and instance segmentation. A compact convolutional stem is integrated for multi-scale representation, forming a hybrid ViT-ConvNet backbone. It achieves significant results on COCO with 51.7 box AP and 46.2 mask AP, showcasing efficiency in training and accuracy in inference through varied sample ratios.