Image Scene Graph Generation (SGG) Benchmark
This provides a standardized benchmark for researchers in fine-grained image understanding, addressing an incremental need for better comparability in SGG model evaluation.
The authors tackled the lack of a standardized benchmark for image scene graph generation (SGG), which hindered comparability of models, by developing a new benchmark based on maskrcnn-benchmark and popular models, and conducted ablation studies using Visual Genome and OpenImages datasets.
There is a surge of interest in image scene graph generation (object, attribute and relationship detection) due to the need of building fine-grained image understanding models that go beyond object detection. Due to the lack of a good benchmark, the reported results of different scene graph generation models are not directly comparable, impeding the research progress. We have developed a much-needed scene graph generation benchmark based on the maskrcnn-benchmark and several popular models. This paper presents main features of our benchmark and a comprehensive ablation study of scene graph generation models using the Visual Genome and OpenImages Visual relationship detection datasets. Our codebase is made publicly available at https://github.com/microsoft/scene_graph_benchmark.