Self-supervised learning (SSL) methods targeting scene images have seen a rapid growth recently, and they mostly rely on either a dedicated dense matching mechanism or a costly unsupervised object discovery module. This paper shows that instead of hinging on these strenuous operations, quality image representations can be learned by treating scene/multi-label image SSL simply as a multi-label classification problem, which greatly simplifies the learning framework. Specifically, multiple binary pseudo-labels are assigned for each input image by comparing its embeddings with those in two dictionaries, and the network is optimized using the binary cross entropy loss. The proposed method is named Multi-Label Self-supervised learning (MLS). Visualizations qualitatively show that clearly the pseudo-labels by MLS can automatically find semantically similar pseudo-positive pairs across different images to facilitate contrastive learning. MLS learns high quality representations on MS-COCO and achieves state-of-the-art results on classification, detection and segmentation benchmarks. At the same time, MLS is much simpler than existing methods, making it easier to deploy and for further exploration.

翻译：针对场景图像的自监督学习方法近期发展迅速，这些方法大多依赖专用的密集匹配机制或代价高昂的无监督目标发现模块。本文表明，无需依赖这些繁复操作，将场景/多标签图像自监督学习简单地视为多标签分类问题，即可学习到高质量的图像表示，这极大简化了学习框架。具体而言，通过将每张输入图像的嵌入与两个字典中的嵌入进行比较，为其分配多个二元伪标签，并使用二元交叉熵损失优化网络。所提方法命名为多标签自监督学习（MLS）。可视化结果清晰表明：MLS生成的伪标签能自动发现不同图像间语义相似的伪正样本对，从而促进对比学习。MLS在MS-COCO数据集上学习到高质量表示，并在分类、检测和分割基准测试中取得最优结果。同时，MLS较现有方法更为简洁，使其更易部署及进一步探索。