search

KaihuaTang / Scene-Graph-Benchmark.pytorch

A new codebase for popular Scene Graph Generation methods (2020). Visualization & Scene Graph Extraction on custom images/datasets are provided. It's also a PyTorch implementation of paper “Unbiased Scene Graph Generation from Biased Training CVPR 2020”
MIT License
1.08k stars 229 forks source link

MOTIFS-SGDet-none and Neural Motifs #9

Open DiligentPanda opened 4 years ago

DiligentPanda commented 4 years ago

Hi, dear author, are these two models, MOTIFS-SGDet-none and Neural Motifs, the same? If not, which one is the baseline listed in the paper.

KaihuaTang commented 4 years ago

MOTIFS-SGDet-none is trained under MODEL.ROI_RELATION_HEAD.PREDICTOR == CausalAnalysisPredictor. There are some slight difference between "CausalAnalysisPredictor + motifs" and original MotifPredictor, which are listed in "Tips and Tricks" of instructions.

In the "unbiased scene graph generation from biased training" paper, the baseline is trained under CausalAnalysisPredictor of course.