no code implementations • 15 Mar 2022 • Xiang Chen, Zhentao Fan, Pengpeng Li, Longgang Dai, Caihua Kong, Zhuoran Zheng, Yufeng Huang, Yufeng Li
Then these negative adversaries are trained end-to-end together with the backbone representation network to enhance the discriminative information and promote factor disentanglement performance by maximizing the adversarial contrastive loss.