arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2003.14142cs.CV
收藏

Look-into-Object:用于目标识别的自监督结构建模

Look-into-Object: Self-supervised Structure Modeling for Object Recognition

Harbin Institute of Technology(哈尔滨工业大学);JD AI Research(京东人工智能研究院)

Mohan Zhou, Yalong Bai, Wei Zhang, Tiejun Zhao, Tao Mei

摘要:

大多数对象识别方法主要集中在学习有区别的视觉模式,而忽略了整体的对象结构。虽然重要,但结构建模通常需要大量的手动注释,因此是劳动密集型的。在本文中,我们提出了“看对象”(明确但本质上建模的对象结构),通过将自我监督到传统的框架。我们表明,识别骨干可以大大增强更强大的表示学习,没有任何额外的注释和推理速度的成本。具体来说,我们首先提出了一个对象范围学习模块,用于根据同一类别中的实例之间共享的视觉模式来定位对象。然后,我们设计了一个空间上下文学习模块,通过预测范围内的相对位置来建模对象的内部结构。这两个模块可以在训练期间轻松插入任何骨干网络,并在推理时分离。大量的实验表明,我们的查找对象方法(LIO)在许多基准测试中实现了很大的性能增益,包括通用对象识别(ImageNet)和细粒度对象识别任务(CUB,汽车,飞机)。我们还表明,这种学习范式是高度概括的其他任务,如目标检测和分割(MS COCO)。项目页面:https://github.com/JDAI-CV/LIO。

英文摘要:

Most object recognition approaches predominantly focus on learning discriminative visual patterns while overlooking the holistic object structure. Though important, structure modeling usually requires significant manual annotations and therefore is labor-intensive. In this paper, we propose to "look into object" (explicitly yet intrinsically model the object structure) through incorporating self-supervisions into the traditional framework. We show the recognition backbone can be substantially enhanced for more robust representation learning, without any cost of extra annotation and inference speed. Specifically, we first propose an object-extent learning module for localizing the object according to the visual patterns shared among the instances in the same category. We then design a spatial context learning module for modeling the internal structures of the object, through predicting the relative positions within the extent. These two modules can be easily plugged into any backbone networks during training and detached at inference time. Extensive experiments show that our look-into-object approach (LIO) achieves large performance gain on a number of benchmarks, including generic object recognition (ImageNet) and fine-grained object recognition tasks (CUB, Cars, Aircraft). We also show that this learning paradigm is highly generalizable to other tasks such as object detection and segmentation (MS COCO). Project page: https://github.com/JDAI-CV/LIO.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑