图 书 馆
上下文感知类别发现的对象图Object-Graphs for Context-Aware Category Discovery |
|
| 课程网址: | http://videolectures.net/cvpr2010_lee_ogca/ |
| 主讲教师: | Yong Jae Lee |
| 开课单位: | 德克萨斯大学 |
| 开课时间: | 2010-07-19 |
| 课程语种: | 英语 |
| 中文简介: |  了解某些类别如何帮助我们在未标记的图像中发现新的类别？无监督的视觉类别发现对于无需人工监督的重复对象的挖掘很有用，但是现有方法没有先验信息，因此对于具有多个对象的混乱场景往往表现不佳。我们建议利用关于先前学习的类别的年龄知识来实现更准确的发现。我们引入了一种新颖的对象图描述符来对相对于陌生区域的对象级别共现模式的布局进行编码，并表明通过使用它来对图像的已知对象和未知对象之间的交互进行建模，我们可以更好地检测新的视觉类别。我们的方法不是从头开始挖掘所有猫的故事，而是在借鉴熟悉对象的有用线索的同时识别新对象。我们评估了基准数据集上的方法，并证明了在发现方面比传统的纯粹基于外观的基线有了明显的改进。 |
| 课程简介: | How can knowing about some categories help us to dis- cover new ones in unlabeled images? Unsupervised visual category discovery is useful to mine for recurring objects without human supervision, but existing methods assume no prior information and thus tend to perform poorly for cluttered scenes with multiple objects. We propose to lever- age knowledge about previously learned categories to en- able more accurate discovery. We introduce a novel object- graph descriptor to encode the layout of object-level co- occurrence patterns relative to an unfamiliar region, and show that by using it to model the interaction between an image’s known and unknown objects we can better de- tect new visual categories. Rather than mine for all cat- egories from scratch, our method identifies new objects while drawing on useful cues from familiar ones. We eval- uate our approach on benchmark datasets and demonstrate clear improvements in discovery over conventional purely appearance-based baselines. |
| 关 键 词: | 布局编码; 建模交互 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2020-11-24：zyk |
| 最后编审: | 2020-12-15：cjy |
| 阅读次数: | 40 |