HyperAIHyperAI超神经

Command Palette

Search for a command to run...

算力平台

Object Detection On Coco

评估指标

AP50
AP75

评测结果

各个模型在此基准测试上的表现结果

Paper Title
DyHead (ResNet-101)64.550.7Dynamic Head: Unifying Object Detection Heads with Attentions
YOLOv7-D6 (44 fps)--YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
EfficientDet-D7 (1536)71.656.9EfficientDet: Scalable and Efficient Object Detection
GFLV2 (ResNeXt-101, 32x4d, DCN)67.653.5Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection
Faster R-CNN (ImageNet+300M)5840.1Revisiting Unreasonable Effectiveness of Data in Deep Learning Era
GLIP (Swin-L, multi-scale)79.567.7Grounded Language-Image Pre-training
Group DETR v281.871.1Group DETR v2: Strong Object Detector with Encoder-Decoder Pretraining
Mask R-CNN (ResNeXt-101-FPN)62.343.4Mask R-CNN
ISTR (ResNet50-FPN-3x, single-scale)--ISTR: End-to-End Instance Segmentation with Transformers
CPNDet (Hourglass-104, multi-scale)67.353.7Corner Proposal Network for Anchor-free, Two-stage Object Detection
M2Det (VGG-16, multi-scale)64.649.3M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network
YOLOv7-E6 (56 fps)--YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
A2MIM (ViT-B)--Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN
D-RFCN + SNIP (ResNet-101, multi-scale)65.548.4An Analysis of Scale Invariance in Object Detection - SNIP
LeYOLO-nano@480--LeYOLO, New Embedded Architecture for Object Detection
Centermask + ResNet10161.646.9CenterMask : Real-Time Anchor-Free Instance Segmentation
AC-FPN Cascade R-CNN (X-152-32x8d-FPN-IN5k, multi scale, only CEM)70.457Attention-guided Context Feature Pyramid Network for Object Detection
MnasFPN (MNASNet-B1)--MnasFPN: Learning Latency-aware Pyramid Architecture for Object Detection on Mobile Devices
Gaussian-FCOS--Localization Uncertainty Estimation for Anchor-Free Object Detection
Faster R-CNN--Speed/accuracy trade-offs for modern convolutional object detectors
0 of 262 row(s) selected.