Uncategorized

• Uncategorized

  • **YoloS**
  • **Yolov7 official** - Yao Wang at all. ['Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors'](https://arxiv.org/abs/2207.02696) YOLOv7 currently outperforms all known real-time object detectors with 30 FPS or higher on GPU V100. YOLOv7-E6 object detector (56 FPS V100, 55.9% AP),
  • Real-Time Object Detection on COCO - **Mean Average Precission (MAP)** - YOLOv6-L6
  • Real-Time Object Detection on COCO - **Speed FPS**
  • Object Detection on COCO - **Mean Average Precission (MAP)** - Co-DETR
  • **Yolov10** - Time End-to-End Object Detection](https://arxiv.org/abs/2405.14458) Yolov10 architecture is similar to YOLOv6 3.0, with an added transformer-based module for better global feature extraction.
  • **Yolo v2**
  • **Yolo v3**
  • **Yolo v4**
  • **Yolo v5** - PyTorch implementation (v1 to v4 Darknet implementation). The major improvements includes mosaic data augmentation and auto learning bounding box anchors
  • **Scaled-Yolo v4** - Yao Wang et al. ['Scaled-YOLOv4: Scaling Cross Stage Partial Network'](https://arxiv.org/abs/2011.08036)
  • **YoloX** - Tiny and YOLOX-Nano outperform YOLOv4-Tiny and NanoDet offering a boost of 10.1% and 1.8% respectively
  • **YoloR** - Yao Wang et al. [‘You Only Learn One Representation: Unified Network for Multiple Tasks’](https://arxiv.org/abs/2105.04206)
  • **YoloF** - level Feature'](https://arxiv.org/abs/2103.09460)
  • **DAMO-YOLO** - Time Object Detection Design'](https://arxiv.org/abs/2211.15444v2) DAMO-YOLO including Neural Architecture Search (NAS), efficient Reparameterized Generalized-FPN (RepGFPN), a lightweight head with AlignedOTA label assignment, and distillation enhancement,
  • **EdgeYOLO** - Real-Time Object Detector'](https://arxiv.org/abs/2302.07483) EdgeYOLO model accuracy of 50.6% AP50:95 and 69.8% AP50 in MS COCO2017 dataset, 26.4% AP50:95 and 44.8% AP50 in VisDrone2019-DET dataset, FPS>=30 on edge-computing device Nvidia Jetson AGX Xavier,
  • **Yolo11**
  • **Yolo-NAS** - AI. They used their proprietary Neural Architecture Search (AutoNAC) to find and optimize a new Deep Learning Architecture Yolo-NAS: number and sizes of the stages, blocks, channels. Using quantization-aware “QSP” and “QCI” modules consisting of QA-RepVGG blocks provide 8-bit quantization and ensuring that model architecture would be compatible with Post-Training Quantization (PTQ) - giving minimal accuracy loss during PTQ. Yolo-NAS also use hybrid quantization method that selectively quantizes specific layers to optimize accuracy and latency tradeoffs as well as the attention mechanism and inference time reparametrization to enhance detection capabilities. Pre-trained weights are available for research use (non-commercial) on SuperGradients, Deci’s PyTorch-based, open-source CV library.
  • **Yolo-World** - World: Real-Time Open-Vocabulary Object Detection'](https://arxiv.org/abs/2401.17270)
  • **Yolov9** - Yao Wang at all. ['YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information'](https://arxiv.org/abs/2402.13616)
  • **Yolov7 not official**
  • **Yolov6 v3.0** - Scale Reloading'](https://arxiv.org/abs/2301.05586v1) YOLOv6-N hits 37.5% AP on the COCO dataset at a throughput of 1187 FPS tested with an NVIDIA Tesla T4 GPU.
  • ‘You Only Look Once: Unified, Real-Time Object Detection’
  • **PP-Yolo** - YOLO: An Effective and Efficient Implementation of Object Detector’](https://arxiv.org/abs/2007.12099). PP-YOLO is based on v3 model with replacement of Darknet 53 backbone of YOLO v3 with a ResNet backbone and increase of training batch size from 64 to 192. Improved mAP to 45.2% (from 43.5 for v4) and FPS from 65 to 73 for Tesla V100 (batch size = 1). Based on PaddlePaddle DL framework
  • **YoloP** - v7) Dong Wu at all. [‘YOLOP: You Only Look Once for Panoptic Driving Perception’](https://arxiv.org/abs/2108.11250). YoloP was designed to perform three visual perception tasks: traffic object detection, drivable area segmentation and lane detection simultaneously in real-time on an embedded device (Jetson TX2, 23 FPS). It is based on one encoder for feature extraction and three decoders to handle the specific tasks
  • ‘YOLO-Z: Improving small object detection in YOLOv5 for autonomous vehicles’
  • **Yolo-ReT** - ReT: Towards High Accuracy Real-time Object Detection on Edge GPUs’](https://arxiv.org/abs/2110.13713)