Contrastive Representation Learning for Gaze Estimation
Contrastive Representation Learning for Gaze Estimation
复制标题
DOI：
10.48550/arxiv.2210.13404
复制
发表时间：
2022-10
期刊：
影响因子：
--
通讯作者：
Swati Jindal;R. Manduchi
中科院分区：
文献类型：
--
作者：
Swati Jindal;R. Manduchi
自监督学习（SSL）已经成为计算机视觉中学习表示的普遍方法。值得注意的是，SSL利用对比学习来鼓励视觉表示在各种图像变换下保持不变。另一方面，凝视估计的任务不仅要求对各种外观的不变性，而且要求对几何变换的等变性。在这项工作中，我们提出了一个用于凝视估计的简单对比表示学习框架，称为凝视对比学习（GazeCLR）。Gazestrium利用多视图数据来促进等方差，并依赖于不改变注视方向的选定数据增强技术来进行不变性学习。我们的实验证明了凝视估计任务的几个设置的Gazebrag的有效性。特别是，我们的研究结果表明，Gazestrium提高了跨域凝视估计的性能，并产生高达17.2%的相对改善。此外，Gazestrium框架与最先进的表示学习方法相比具有竞争力，可以进行少量评估。代码和预训练模型可在https://github.com/jswati31/gazeclr上获得。
Self-supervised learning (SSL) has become prevalent for learning representations in computer vision. Notably, SSL exploits contrastive learning to encourage visual representations to be invariant under various image transformations. The task of gaze estimation, on the other hand, demands not just invariance to various appearances but also equivariance to the geometric transformations. In this work, we propose a simple contrastive representation learning framework for gaze estimation, named Gaze Contrastive Learning (GazeCLR). GazeCLR exploits multi-view data to promote equivariance and relies on selected data augmentation techniques that do not alter gaze directions for invariance learning. Our experiments demonstrate the effectiveness of GazeCLR for several settings of the gaze estimation task. Particularly, our results show that GazeCLR improves the performance of cross-domain gaze estimation and yields as high as 17.2% relative improvement. Moreover, the GazeCLR framework is competitive with state-of-the-art representation learning methods for few-shot evaluation. The code and pre-trained models are available at https://github.com/jswati31/gazeclr.