双头判别器实现持续域对抗适应
Continual Domain Adversarial Adaptation via Double-Head Discriminators
AI总结：
针对持续域对抗适应中源域数据受限导致$\gH$-散度估计误差的问题，提出双头判别器算法，引入源专用判别器降低估计误差，在基准上提升超2%并缓解遗忘。
摘要：
在持续学习环境中进行域对抗适应面临重大挑战，因为访问先前源域数据受到限制。尽管持续学习领域已有广泛研究，但在记忆回放方法的标准设置下，仅利用少量存储的源域数据无法有效完成对抗适应任务。这一局限性源于使用少量源域样本对$\gH$-散度进行经验估计时产生的误差。为解决此问题，我们提出了一种双头判别器算法，通过引入一个仅在源学习阶段训练的额外源专用域判别器。我们证明，引入预训练的源专用域判别器后，从源域侧降低了与$\gH$-散度相关的对抗损失的经验估计误差。在现有域适应基准上的进一步实验表明，我们提出的算法在所有类别的目标域适应任务上实现了超过2%的提升，同时显著缓解了对源域的遗忘。
英文摘要：
Domain adversarial adaptation in a continual setting poses a significant challenge due to the limitations on accessing previous source domain data. Despite extensive research in continual learning, the task of adversarial adaptation cannot be effectively accomplished using only a small number of stored source domain data, which is a standard setting in memory replay approaches. This limitation arises from the erroneous empirical estimation of $\gH$-divergence with few source domain samples. To tackle this problem, we propose a double-head discriminator algorithm, by introducing an addition source-only domain discriminator that are trained solely on source learning phase. We prove that with the introduction of a pre-trained source-only domain discriminator, the empirical estimation error of $\gH$-divergence related adversarial loss is reduced from the source domain side. Further experiments on existing domain adaptation benchmark show that our proposed algorithm achieves more than 2$\%$ improvement on all categories of target domain adaptation task while significantly mitigating the forgetting on source domain.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
