通过拼接单物体图像提升多物体无监督表征效果
Multiple Object Stitching for Unsupervised Representation Learning
- 用单物体图像拼接生成多物体图像，自动获得物体对应关系
- 在ImageNet、COCO等数据集上超越现有无监督方法
- 适合需要精细物体表征的任务如检测与分割
针对单物体中心图像的对比学习在无监督表征上取得显著进展，但在普遍存在的多物体图像上表现不佳。本文提出一种简单而有效的方法——多物体拼接（Multiple Object Stitching, MOS），用于优化多物体图像的无监督表征。具体地，通过拼接单物体中心图像构建多物体图像，其中物体位置预先设定。相比现有对比方法，该方法无需人工标注即可提供多物体图像间的物体对应关系，使模型更关注每个物体的表征，从而为复杂下游任务（如目标检测和语义分割）提供更细致的表示。在ImageNet、CIFAR和COCO数据集上的实验表明，所提方法在单物体和多物体图像上均达到领先的无监督表征性能。代码已开源。
原文摘要 · Abstract (English)
Contrastive learning for single object centric images has achieved remarkable progress on unsupervised representation, but suffering inferior performance on the widespread images with multiple objects. In this paper, we propose a simple but effective method, Multiple Object Stitching (MOS), to refine the unsupervised representation for multi-object images. Specifically, we construct the multi-object images by stitching the single object centric ones, where the objects in the synthesized multi-object images are predetermined. Hence, compared to the existing contrastive methods, our method provides additional object correspondences between multi-object images without human annotations. In this manner, our method pays more attention to the representations of each object in multi-object image, thus providing more detailed representations for complicated downstream tasks, such as object detection and semantic segmentation. Experimental results on ImageNet, CIFAR and COCO datasets demonstrate that our proposed method achieves the leading unsupervised representation performance on both single object centric images and multi-object ones. The source code is available at https://github.com/visresearch/MultipleObjectStitching.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。