论文标题
在测试时间期间引入中间域以进行有效自我训练
Introducing Intermediate Domains for Effective Self-Training during Test-Time
论文作者
论文摘要
在实践中，在测试时间期间经历域变化几乎是不可避免的，可能导致严重的性能降解。为了克服此问题，测试时间适应在部署过程中继续更新初始源模型。一个有希望的方向是基于自我训练的方法，该方法已证明非常适合逐渐适应，因为可以提供可靠的伪标记。在这项工作中，我们解决了在测试时间适应设置中应用自我训练时存在的两个问题。首先，将模型调整为包含多个域的长测试序列可能会导致误差积累。其次，自然而然地，并非所有的转移在实践中逐渐逐渐。为了应对这些挑战，我们介绍了GTTA。通过创建人工中间域将当前域转移到更逐渐的区域中，可以通过高质量的伪标签进行有效的自我训练。为了创建中间域，我们提出了两个独立的变体：混合和轻巧样式转移。我们证明了我们的方法对持续和逐步腐败基准以及Imagenet-R的有效性。为了进一步调查城市场景细分的逐渐变化，我们发布了一个新的基准：Carlatta。它可以探索几个非平稳域的变化。
Experiencing domain shifts during test-time is nearly inevitable in practice and likely results in a severe performance degradation. To overcome this issue, test-time adaptation continues to update the initial source model during deployment. A promising direction are methods based on self-training which have been shown to be well suited for gradual domain adaptation, since reliable pseudo-labels can be provided. In this work, we address two problems that exist when applying self-training in the setting of test-time adaptation. First, adapting a model to long test sequences that contain multiple domains can lead to error accumulation. Second, naturally, not all shifts are gradual in practice. To tackle these challenges, we introduce GTTA. By creating artificial intermediate domains that divide the current domain shift into a more gradual one, effective self-training through high quality pseudo-labels can be performed. To create the intermediate domains, we propose two independent variations: mixup and light-weight style transfer. We demonstrate the effectiveness of our approach on the continual and gradual corruption benchmarks, as well as ImageNet-R. To further investigate gradual shifts in the context of urban scene segmentation, we publish a new benchmark: CarlaTTA. It enables the exploration of several non-stationary domain shifts.
