基于以槽为中心的模型的测试时适应
Test-time Adaptation with Slot-Centric Models
- Carnegie Mellon University（卡内基梅隆大学）
- Mila（米拉研究所）
- DeepMind（深度思维）
- Google Research（谷歌研究院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对视觉检测器在分布外场景分解能力不足的问题，提出半监督的以槽为中心的模型Slot-TTA，通过在测试时对重建或跨视图合成目标进行梯度下降适应，显著提升了图像和3D点云的分布外泛化性能。
AI中文摘要：
当前的视觉检测器虽然在训练分布内表现出色，但通常无法将分布外场景解析为其组成实体。最近的测试时适应方法使用辅助自监督损失，将网络参数独立地适应于每个测试样本，并在图像分类任务的训练分布外泛化方面展现出有希望的结果。在我们的工作中，我们发现如果不考虑架构的归纳偏置，这些损失对于场景分解任务是不充分的。最近的以槽为中心的生成模型试图通过重建像素，以自监督的方式将场景分解为实体。基于这两项工作，我们提出了Slot-TTA，这是一种半监督的以槽为中心的场景分解模型，在测试时通过在重建或跨视图合成目标上进行梯度下降，对每个场景进行适应。我们在多种输入模态（图像或3D点云）上评估了Slot-TTA，并表明相对于最先进的监督前馈检测器和其他测试时适应方法，在分布外性能上取得了显著改进。
英文摘要：
Current visual detectors, though impressive within their training distribution, often fail to parse out-of-distribution scenes into their constituent entities. Recent test-time adaptation methods use auxiliary self-supervised losses to adapt the network parameters to each test example independently and have shown promising results towards generalization outside the training distribution for the task of image classification. In our work, we find evidence that these losses are insufficient for the task of scene decomposition, without also considering architectural inductive biases. Recent slot-centric generative models attempt to decompose scenes into entities in a self-supervised manner by reconstructing pixels. Drawing upon these two lines of work, we propose Slot-TTA, a semi-supervised slot-centric scene decomposition model that at test time is adapted per scene through gradient descent on reconstruction or cross-view synthesis objectives. We evaluate Slot-TTA across multiple input modalities, images or 3D point clouds, and show substantial out-of-distribution performance improvements against state-of-the-art supervised feed-forward detectors, and alternative test-time adaptation methods.
