Towards Reversal-Invariant Image Representation
作者: Lingxi XieJingdong WangWeiyao LinBo ZhangQi Tian
作者单位: 1The Johns Hopkins University
2Microsoft Research
3Shanghai Jiao Tong University
4Tsinghua University
5University of Texas at San Antonio
刊名: International Journal of Computer Vision, 2017, Vol.123 (2), pp.226-250
来源数据库: Springer Nature Journal
DOI: 10.1007/s11263-016-0970-x
关键词: Image classificationBoFCNNReversal-invariant image representation
英文摘要: State-of-the-art image classification approaches are mainly based on robust image representation, such as the bag-of-features (BoF) model or the convolutional neural network (CNN) architecture. In real applications, the orientation (left/right) of an image or an object might vary from sample to sample, whereas some handcrafted descriptors (e.g., SIFT) and network operations (e.g., convolution) are not reversal-invariant, leading to the unsatisfied stability of image features extracted from these models. To deal with, a popular solution is to augment the dataset by adding a left-right reversed copy for each image. This strategy improves the recognition accuracy to some extent, but also brings the price of almost doubled time and memory consumptions on both the training and testing stages....
原始语种摘要: State-of-the-art image classification approaches are mainly based on robust image representation, such as the bag-of-features (BoF) model or the convolutional neural network (CNN) architecture. In real applications, the orientation (left/right) of an image or an object might vary from sample to sample, whereas some handcrafted descriptors (e.g., SIFT) and network operations (e.g., convolution) are not reversal-invariant, leading to the unsatisfied stability of image features extracted from these models. To deal with, a popular solution is to augment the dataset by adding a left-right reversed copy for each image. This strategy improves the recognition accuracy to some extent, but also brings the price of almost doubled time and memory consumptions on both the training and testing stages....
全文获取路径: Springer Nature  (合作)
分享到:
来源刊物:
影响因子:3.623 (2012)

×
关键词翻译
关键词翻译
  • invariant 不变量
  • convolution 褶积
  • image 
  • recognition 识别
  • right 右边的
  • features 特征
  • representation 表现
  • orientation 定向
  • scene 景物
  • popular 普及