论文标题
CODO：与检测的下游背景不变性的对比度学习
CoDo: Contrastive Learning with Downstream Background Invariance for Detection
论文作者
论文摘要
先前的自我监督学习研究主要选择图像级实例歧视作为借口任务。它实现了出色的分类性能，可与监督的学习方法相媲美。但是，随着在下游任务（例如对象检测）上的转移性能下降。为了弥合性能差距，我们提出了一种新颖的对象级别的自我监督学习方法，称为“对比度学习”，其下游背景不变性（CODO）。借口任务转换为各种背景的实例位置建模，尤其是对于下游数据集。背景不变性的能力对于对象检测至关重要。首先，提出了一个数据增强策略，以将实例粘贴到背景图像上，然后抖动边界框以涉及背景信息。其次，我们在预处理网络和主流检测管道之间实现架构对齐。第三，层次结构和多视图对比学习旨在提高视觉表示学习的性能。 Mscoco上的实验表明，提出的带有常见骨架的CODO RESNET50-FPN可为对象检测产生强大的传递学习结果。
The prior self-supervised learning researches mainly select image-level instance discrimination as pretext task. It achieves a fantastic classification performance that is comparable to supervised learning methods. However, with degraded transfer performance on downstream tasks such as object detection. To bridge the performance gap, we propose a novel object-level self-supervised learning method, called Contrastive learning with Downstream background invariance (CoDo). The pretext task is converted to focus on instance location modeling for various backgrounds, especially for downstream datasets. The ability of background invariance is considered vital for object detection. Firstly, a data augmentation strategy is proposed to paste the instances onto background images, and then jitter the bounding box to involve background information. Secondly, we implement architecture alignment between our pretraining network and the mainstream detection pipelines. Thirdly, hierarchical and multi views contrastive learning is designed to improve performance of visual representation learning. Experiments on MSCOCO demonstrate that the proposed CoDo with common backbones, ResNet50-FPN, yields strong transfer learning results for object detection.
