Pytorch code for our ECCV 2018 paper "Graph R-CNN for Scene Graph Generation"
This project is a set of reimplemented representative scene graph generation models based on Pytorch 1.0, including:
- Graph R-CNN for Scene Graph Generation, our own. ECCV 2018.
- Scene Graph Generation by Iterative Message Passing, Xu et al. CVPR 2017
- Scene Graph Generation from Objects, Phrases and Region Captions, Li et al. ICCV 2017
- Neural Motifs: Scene Graph Parsing with Global Context, Zellers et al. CVPR 2018
Our reimplementations are based on the following repositories:
The goal of gathering all these representative methods into a single repo is to establish a more fair comparison across different methods under the same settings. As you may notice in recent literatures, the reported numbers for IMP, MSDN, Graph R-CNN and Neural Motifs are usually confusing, especially due to the big gap between IMP style methods (first three) and Neural Motifs-style methods (neural motifs paper and other variants built on it). We hope this repo can establish a good benchmark for various scene graph generation methods, and contribute to the research community!
- Faster R-CNN Baseline (:balloon: 2019-07-04)
- Scene Graph Generation Baseline (:balloon: 2019-07-06)
- Iterative Message Passing (IMP) (:balloon: 2019-07-07)
- Multi-level Scene Description Network (MSDN)
- Neural Motif (Frequency Prior Baseline) (:balloon: 2019-07-08)
- Neural Motif
- Graph R-CNN
backbone | model | bs | lr | lr_decay_step | max_iter | mAP@0.5 | mAP@0.50:0.95 |
---|---|---|---|---|---|---|---|
Resnet-101 | faster r-cnn | 6 | 5e-3 | (70k, 90k) | 100k | 24.8 | 12.8 |
backbone | model | bs | lr | lr_decay_step | max_iter | sgdet@20 | sgdet@50 | sgdet@100 |
---|---|---|---|---|---|---|---|---|
Resnet-101 | vanilla | 6 | 5e-3 | (70k, 90k) | 100k | 10.4 | 14.3 | 16.8 |
Resnet-101 | frequency | 6 | 5e-3 | (70k, 90k) | 100k | 19.4 | 25.0 | 28.5 |