316 code implementations • 8 Apr 2018 • Joseph Redmon, Ali Farhadi
At 320x320 YOLOv3 runs in 22 ms at 28. 2 mAP, as accurate as SSD but three times faster.
Ranked #5 on Robust Object Detection on Cityscapes
Classification One-stage Anchor-free Oriented Object Detection +2
1 code implementation • CVPR 2018 • Kiana Ehsani, Hessam Bagherinezhad, Joseph Redmon, Roozbeh Mottaghi, Ali Farhadi
We introduce the task of directly modeling a visually intelligent agent.
1 code implementation • CVPR 2018 • Daniel Gordon, Aniruddha Kembhavi, Mohammad Rastegari, Joseph Redmon, Dieter Fox, Ali Farhadi
Our experiments show that our proposed model outperforms popular single controller based methods on IQUAD V1.
233 code implementations • CVPR 2017 • Joseph Redmon, Ali Farhadi
On the 156 classes not in COCO, YOLO9000 gets 16. 0 mAP.
Ranked #8 on Object Detection on UA-DETRAC
18 code implementations • 16 Mar 2016 • Mohammad Rastegari, Vicente Ordonez, Joseph Redmon, Ali Farhadi
We propose two efficient approximations to standard convolutional neural networks: Binary-Weight-Networks and XNOR-Networks.
Ranked #10 on Classification with Binary Neural Network on ImageNet
145 code implementations • CVPR 2016 • Joseph Redmon, Santosh Divvala, Ross Girshick, Ali Farhadi
A single neural network predicts bounding boxes and class probabilities directly from full images in one evaluation.
Ranked #1 on Real-Time Object Detection on PASCAL VOC 2007
3 code implementations • 9 Dec 2014 • Joseph Redmon, Anelia Angelova
We present an accurate, real-time approach to robotic grasp detection based on convolutional neural networks.
Ranked #5 on Robotic Grasping on Cornell Grasp Dataset