Meta Spatio-Temporal Debiasing for Video Scene Graph Generation
This work addresses generalization issues in video scene graph generation for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles the spatio-temporal conditional bias problem in video scene graph generation caused by long-tailed training data, proposing a meta-learning framework that improves generalization by optimizing performance on biased query sets after training on a support set, with extensive experiments validating its efficacy.
Video scene graph generation (VidSGG) aims to parse the video content into scene graphs, which involves modeling the spatio-temporal contextual information in the video. However, due to the long-tailed training data in datasets, the generalization performance of existing VidSGG models can be affected by the spatio-temporal conditional bias problem. In this work, from the perspective of meta-learning, we propose a novel Meta Video Scene Graph Generation (MVSGG) framework to address such a bias problem. Specifically, to handle various types of spatio-temporal conditional biases, our framework first constructs a support set and a group of query sets from the training data, where the data distribution of each query set is different from that of the support set w.r.t. a type of conditional bias. Then, by performing a novel meta training and testing process to optimize the model to obtain good testing performance on these query sets after training on the support set, our framework can effectively guide the model to learn to well generalize against biases. Extensive experiments demonstrate the efficacy of our proposed framework.