└── README.md


/README.md:
--------------------------------------------------------------------------------
 1 | # BGNN-SGG
 2 | [![LICENSE](https://img.shields.io/badge/license-MIT-green)](https://github.com/KaihuaTang/Scene-Graph-Benchmark.pytorch/blob/master/LICENSE)
 3 | [![Python](https://img.shields.io/badge/python-3.7-blue.svg)](https://www.python.org/)
 4 | ![PyTorch](https://img.shields.io/badge/pytorch-1.4.0-%237732a8)
 5 | 
 6 | Our paper [Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generation](https://arxiv.org/abs/2104.00308) has been accepted by CVPR 2021.
 7 | 
 8 | We have release the related code in [PySGG project](https://github.com/SHTUPLUS/PySGG) with other SGG models. Feel free to play with the PySGG
 9 | 
10 | 
11 | ### VG
12 | | Model(SGGen) | mR@50 | mR@100 | R@50 | R@100 | head | body | tail |
13 | |--------------|:-----:|:------:|:----:|:-----:|------|------|------|
14 | | BGNN         |  10.9 |  13.55 | 29.8 |  34.6 | 33.4 | 13.4 | 6.4  |
15 | 
16 | 
17 | ### OIv6
18 | | Model(SGGen) | mR@50 | R@50 | wmAP_rel | wmAP_phr | score_wtd |
19 | |---|:---:|:---:|:---:|:---:|---|
20 | | BGNN | 41.71 | 74.96 | 33.83 | 34.87 | 42.47 |
21 | 


--------------------------------------------------------------------------------