...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Multimedia, IEEE Transactions on >Task-Driven Progressive Part Localization for Fine-Grained Object Recognition
【24h】

Task-Driven Progressive Part Localization for Fine-Grained Object Recognition

机译：任务驱动的渐进式零件本地化，用于细粒度的对象识别

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The problem of fine-grained object recognition is very challenging due to the subtle visual differences between different object categories. In this paper, we propose a task-driven progressive part localization (TPPL) approach for fine-grained object recognition. Most existing methods follow a two-step approach that first detects salient object parts to suppress the interference from background scenes and then classifies objects based on features extracted from these regions. The part detector and object classifier are often independently designed and trained. In this paper, our major finding is that the part detector should be jointly designed and progressively refined with the object classifier so that the detected regions can provide the most distinctive features for final object recognition. Specifically, we develop a part-based SPP-net (Part-SPP) as our baseline part detector. We then establish a TPPL framework, which takes the predicted boxes of Part-SPP as an initial guess, and then examines new regions in the neighborhood using a particle swarm optimization approach, searching for more discriminative image regions to maximize the objective function and the recognition performance. This procedure is performed in an iterative manner to progressively improve the joint part detection and object classification performance. Experimental results on the Caltech-UCSD-200-2011 dataset demonstrate that our method outperforms state-of-the-art fine-grained categorization methods both in part localization and classification, even without requiring a bounding box during testing.
机译：由于不同对象类别之间的细微视觉差异，细粒度对象识别问题非常具有挑战性。在本文中，我们提出了一种任务驱动的渐进零件定位（TPPL）方法，用于细粒度的对象识别。大多数现有方法遵循两步方法，该方法首先检测显着的对象部分以抑制来自背景场景的干扰，然后根据从这些区域提取的特征对对象进行分类。零件检测器和对象分类器通常是独立设计和训练的。在本文中，我们的主要发现是，零件检测器应与目标分类器共同设计并逐步完善，以使检测到的区域能够为最终目标识别提供最鲜明的特征。具体来说，我们开发了基于零件的SPP网络（Part-SPP）作为我们的基准零件检测器。然后，我们建立一个TPPL框架，该框架将Part-SPP的预测框作为初始猜测，然后使用粒子群优化方法检查邻域中的新区域，搜索更具区分性的图像区域，以最大化目标函数和识别能力性能。此过程以迭代方式执行，以逐步提高关节部位检测和对象分类性能。在Caltech-UCSD-200-2011数据集上的实验结果表明，即使在测试过程中不需要边界框，我们的方法在部分本地化和分类方面也优于最新的细粒度分类方法。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号