Gradual Domain Adaptation without Indexed Intermediate Domains
Gradual Domain Adaptation without Indexed Intermediate Domains
复制标题
DOI：
10.48550/arxiv.2207.04587
复制
发表时间：
2022-07
期刊：
影响因子：
--
通讯作者：
Hong-You Chen;Wei-Lun Chao
中科院分区：
文献类型：
--
作者：
Hong-You Chen;Wei-Lun Chao
当源域和目标域之间存在较大差异时，无监督域自适应的有效性会降低。逐渐域适应（GDA）是一种很有前途的方法来缓解这种问题，通过利用额外的未标记的数据，逐渐从源转移到目标。通过顺序地适应模型沿着“索引“的中间域，GDA大大提高了整体适应性能。然而，在实践中，额外的未标记的数据可能不会被分离到中间域和索引正确，限制了GDA的适用性。在本文中，我们研究如何发现的序列时，它是不是已经可用的中间域。具体地说，我们提出了一个由粗到细的框架，它通过渐进的域搜索训练从粗域发现步骤开始。然后，该粗域序列通过新的循环一致性损失经历精细索引步骤，这鼓励下一个中间域保留当前中间域的足够的判别知识。然后可以通过GDA算法使用所得的结构域序列。在GDA的基准数据集上，我们证明了我们的方法，我们称之为中间DOmain标签（IDOL），与预定义的域序列相比，可以导致相当甚至更好的适应性能，使GDA对域序列的质量更适用和鲁棒。代码可在https://github.com/hongyouc/IDOL上获得。
The effectiveness of unsupervised domain adaptation degrades when there is a large discrepancy between the source and target domains. Gradual domain adaptation (GDA) is one promising way to mitigate such an issue, by leveraging additional unlabeled data that gradually shift from the source to the target. Through sequentially adapting the model along the"indexed"intermediate domains, GDA substantially improves the overall adaptation performance. In practice, however, the extra unlabeled data may not be separated into intermediate domains and indexed properly, limiting the applicability of GDA. In this paper, we investigate how to discover the sequence of intermediate domains when it is not already available. Concretely, we propose a coarse-to-fine framework, which starts with a coarse domain discovery step via progressive domain discriminator training. This coarse domain sequence then undergoes a fine indexing step via a novel cycle-consistency loss, which encourages the next intermediate domain to preserve sufficient discriminative knowledge of the current intermediate domain. The resulting domain sequence can then be used by a GDA algorithm. On benchmark data sets of GDA, we show that our approach, which we name Intermediate DOmain Labeler (IDOL), can lead to comparable or even better adaptation performance compared to the pre-defined domain sequence, making GDA more applicable and robust to the quality of domain sequences. Codes are available at https://github.com/hongyouc/IDOL.