Resistance Training Using Prior Bias: Toward Unbiased Scene Graph Generation


  • Chao Chen School of Computer Science, Wuhan University JD Explore Academy Hubei Key Laboratory of Multimedia and Network Communication Engineering Institute of Artificial Intelligence, Wuhan University National Engineering Research Center for Multimedia Software, Wuhan University
  • Yibing Zhan JD Explore Academy
  • Baosheng Yu The University of Sydney
  • Liu Liu The University of Sydney
  • Yong Luo School of Computer Science, Wuhan University
  • Bo Du School of Computer Science, Wuhan University



Computer Vision (CV)


Scene Graph Generation (SGG) aims to build a structured representation of a scene using objects and pairwise relationships, which benefits downstream tasks. However, current SGG methods usually suffer from sub-optimal scene graph generation because of the long-tailed distribution of training data. To address this problem, we propose Resistance Training using Prior Bias (RTPB) for the scene graph generation. Specifically, RTPB uses a distributed-based prior bias to improve models' detecting ability on less frequent relationships during training, thus improving the model generalizability on tail categories. In addition, to further explore the contextual information of objects and relationships, we design a contextual encoding backbone network, termed as Dual Transformer (DTrans). We perform extensive experiments on a very popular benchmark, VG150, to demonstrate the effectiveness of our method for the unbiased scene graph generation. In specific, our RTPB achieves an improvement of over 10% under the mean recall when applied to current SGG methods. Furthermore, DTrans with RTPB outperforms nearly all state-of-the-art methods with a large margin. Code is available at




How to Cite

Chen, C., Zhan, Y., Yu, B., Liu, L., Luo, Y., & Du, B. (2022). Resistance Training Using Prior Bias: Toward Unbiased Scene Graph Generation. Proceedings of the AAAI Conference on Artificial Intelligence, 36(1), 212-220.



AAAI Technical Track on Computer Vision I