In this paper, we propose a novel self-supervised representation learning method, Self-EMD, for object detection. Our method directly trained on unlabeled non-iconic image dataset like COCO, instead of commonly used iconic-object image dataset like ImageNet. We keep the convolutional feature maps as the image embedding to preserve spatial structures and adopt Earth Mover's Distance (EMD) to compute the similarity between two embeddings. Our Faster R-CNN (ResNet50-FPN) baseline achieves 39.8% mAP on COCO, which is on par with the state of the art self-supervised methods pre-trained on ImageNet. More importantly, it can be further improved to 40.4% mAP with more unlabeled images, showing its great potential for leveraging more easily obtained unlabeled data. Code will be made available.

本文提出一种新颖的自监督表示学习方法Self-EMD，用于目标检测。我们直接使用未标记的非图标图像数据集进行训练，而不是像ImageNet这样常用的图标对象图像数据集。我们将卷积特征映射保留为图像嵌入，以保留空间结构，并采用地球移动距离（EMD）来计算两个嵌入之间的相似性。我们的Faster R-CNN（ResNet50-FPN）基线在COCO上实现了39.8％的mAP，与在ImageNet上预训练的最先进的自监督方法相当。更重要的是，它可以在更多未标记图像的情况下进一步提高至40.4％的mAP，展示了更易获得的未标记数据的巨大潜力。

Self-EMD：无需ImageNet的自监督物体检测