Label Semantic Knowledge Distillation for Unbiased Scene Graph Generation

• Published in: IEEE transactions on circuits and systems for video technology Vol. 34; no. 1; pp. 195 - 206
• Main Authors: Li, Lin, Xiao, Jun, Shi, Hanrong, Wang, Wenxiao, Shao, Jian, Liu, An-An, Yang, Yi, Chen, Long
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.01.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Ablation; Annotations; Classification; Distillation; Image analysis; Iterative methods; Knowledge discovery; knowledge distillation; label confusion; Labels; Object detection; Predictive models; Semantics; Training; Unbiased scene graph generation; Visualization

The Scene Graph Generation (SGG) task aims to detect all the objects and their pairwise visual relationships in a given image. Although SGG has achieved remarkable progress over the last few years, almost all existing SGG models follow the same training paradigm: they treat both object and predicate...