Unbiased Scene Graph Generation from Biased Training

Today's scene graph generation (SGG) task is still far from practical, mainly due to the severe training bias, e.g., collapsing diverse "human walk on / sit on / lay on beach" into "human on beach". Given such SGG, the down-stream tasks such as VQA can hardly infer better scene structures than merely a bag of objects... (read more)

PDF Abstract CVPR 2020 PDF CVPR 2020 Abstract

Datasets


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Scene Graph Generation Visual Genome Causal-TDE Recall@50 31.93 # 1
mean Recall @20 6.9 # 3

Methods used in the Paper


METHOD TYPE
Causal Inference