Visual Perception 2D Object Detection CNN YOLOv1 YOLOv3 FCOS Faster RCNN Custom naive detection net SSD RetinaNet Transformer ViT (classification) DETR Deformable DETR RT-DETR 2D Segmentation U-Net DeepLab 3D Object Detection CNN Transformer Object Tracking Simple Online and Real-time Tracking (SORT) DeepSORT ByteTrack BoT-SORT