论文标题
具有几何集一致性的自我监督图像表示学习
Self-Supervised Image Representation Learning with Geometric Set Consistency
论文作者
论文摘要
我们提出了一种在3D几何一致性的指导下进行自我监督图像表示学习的方法。我们的直觉是，3D几何一致性先验（如光滑区域和表面不连续性）可能意味着语义或对象边界一致，并且可以作为指导没有语义标签的2D图像表示的强大提示。具体而言，我们将3D几何一致性引入了对比度学习框架，以在图像视图中执行特征一致性。我们建议将几何一致性集用作约束，并相应地适应Infonce损失。我们证明我们学到的图像表示是一般的。通过对基于2D图像的各种下游任务进行细化我们的预训练表示，包括语义分割，对象检测和实例分割，对现实世界室内场景数据集，我们与最先进的方法相比实现了卓越的性能。
We propose a method for self-supervised image representation learning under the guidance of 3D geometric consistency. Our intuition is that 3D geometric consistency priors such as smooth regions and surface discontinuities may imply consistent semantics or object boundaries, and can act as strong cues to guide the learning of 2D image representations without semantic labels. Specifically, we introduce 3D geometric consistency into a contrastive learning framework to enforce the feature consistency within image views. We propose to use geometric consistency sets as constraints and adapt the InfoNCE loss accordingly. We show that our learned image representations are general. By fine-tuning our pre-trained representations for various 2D image-based downstream tasks, including semantic segmentation, object detection, and instance segmentation on real-world indoor scene datasets, we achieve superior performance compared with state-of-the-art methods.
