Unsupervised contrastive learning achieves great success in learning image representations with CNN. Unlike most recent methods that focused on improving accuracy of image classification, we present a novel contrastive learning approach, named DetCo, which fully explores the contrasts between global image and local image patches to learn discriminative representations for object detection. DetCo has several appealing benefits. (1) It is carefully designed by investigating the weaknesses of current self-supervised methods, which discard important representations for object detection. (2) DetCo builds hierarchical intermediate contrastive losses between global image and local patches to improve object detection, while maintaining global representations for image recognition. Theoretical analysis shows that the local patches actually remove the contextual information of an image, improving the lower bound of mutual information for better contrastive learning. (3) Extensive experiments on PASCAL VOC, COCO and Cityscapes demonstrate that DetCo not only outperforms state-of-the-art methods on object detection, but also on segmentation, pose estimation, and 3D shape prediction, while it is still competitive on image classification. For example, on PASCAL VOC, DetCo-100ep achieves 57.4 mAP, which is on par with the result of MoCov2-800ep. Moreover, DetCo consistently outperforms supervised method by 1.6/1.2/1.0 AP on Mask RCNN-C4/FPN/RetinaNet with 1x schedule. Code will be released at \href{https://github.com/xieenze/DetCo}{\color{blue}{\tt github.com/xieenze/DetCo}} and \href{https://github.com/open-mmlab/OpenSelfSup}{\color{blue}{\tt github.com/open-mmlab/OpenSelfSup}}.

翻译：未经监督的对比学习在与CNN的图像演示中取得了巨大成功。 与最近侧重于提高图像分类准确性的方法{ 最近侧重于提高图像分类准确性的方法{ 不同的是,我们展示了一种新型的对比学习方法,名为DetCo,它充分探索了全球图像和本地图像补丁之间的对比,以了解用于检测物体的区别性表现。 DotCo有若干令人感兴趣的好处。 (1) 它通过调查当前自我监督方法的弱点而精心设计,这些方法摒弃了对物体探测的重要表现。 (2) DetCo在全球图像和本地补丁之间建立起等级的中间对比性损失,以改进物体探测,同时保持全球图像识别。理论分析表明,本地补丁实际上删除了图像的背景信息,改进了相互信息的较低范围,以更好地进行对比性学习。 (3) PASCAL VOC、COOCO和城市景象的广泛实验表明,DOCO不仅在目标检测上优于状态,而且还在分解、显示估计和3DFSO/OIO 上,在图像分类上仍然具有竞争力。