Haichao Zhang
ABSTRACT
We address the problem of image representation with user click data, wherein each image is represented as a count vector based on its clicked queries. As the query set obtained from search engines is large-scale and redundant, this image representation is extremely high-dimensional and with low discriminative ability. To deal with this issue, we propose a deep click feature based query clustering approach, and construct a compact and low-dimensional click feature with merged queries. Specially, to learn the deep click feature, we construct a smooth image-click graph instead of the direct image-click vector to represent each query, and use it as the input of the convolutional network. A similarity graph based re-sorting and propagation method is applied to construct the click graph. We evaluate our method on the public Clickture-Dog dataset. Experimental results show that: 1) Query merging with image-click graph outperforms that with image-click vector, since it improves the click-unbalance among categories and captures more structured information; 2) The deep model helps to generate a powerful hierarchical click feature for queries, making an improved clustering result.
- Rudi L. Cilibrasi and Paul M. B. Vitanyi. 2007. The Google Similarity Distance. IEEE Transactions on Knowledge & Data Engineering 19, 3 (2007), 370--383. Google Scholar
Digital Library
- Kamran Ghasedi Dizaji, Amirhossein Herandi, Cheng Deng, Weidong Cai, and Heng Huang. 2017. Deep Clustering via Joint Convolutional Autoencoder Embedding and Relative Entropy Minimization. (2017).Google Scholar
- Linan Feng and Bir Bhanu. 2016. Semantic Concept Co-occurrence Patterns for Image Annotation and Retrieval. IEEE Trans Pattern Anal Mach Intell 38, 4 (2016), 785--799. Google ScholarDigital Library
- Wu Feng and Dong Liu. 2017. Fine-Grained Image Recognition from Click-Through Logs Using Deep Siamese Network. In International Conference on Multimedia Modeling. 127--138.Google ScholarCross Ref
- Xian Sheng Hua, Linjun Yang, Jingdong Wang, Jing Wang, Ming Ye, Kuansan Wang, Yong Rui, and Jin Li. 2013. Clickage: towards bridging semantic and intent gaps via mining click logs of search engines. In ACM International Conference on Multimedia. 243--252. Google ScholarDigital Library
- Hong Shao, Shuang Chen, Jie Yi Zhao, Wen Cheng Cui, and Y. U. Tian-Shu. 2015. Face recognition based on subset selection via metric learning on manifold. Frontiers of Information Technology & Electronic Engineering 16, 12 (2015), 1046--1058.Google ScholarCross Ref
- Min Tan, Zhenfang Hu, Baoyuan Wang, Jieyi Zhao, and Yueming Wang. 2016. Robust object recognition via weakly supervised metric and template learning. Neurocomputing 101 (2016), 96--107. Google ScholarDigital Library
- Min Tan, Gang Pan, Yueming Wang, Yuting Zhang, and Zhaohui Wu. 2014. L1-norm latent SVM for compact features in object detection. Neurocomputing 139, 139 (2014), 56--64. Google ScholarDigital Library
- M. Tan, B. Wang, Z. Wu, J. Wang, and G. Pan. 2016. Weakly Supervised Metric Learning for Traffic Sign Recognition in a LIDAR-Equipped Vehicle. IEEE Transactions on Intelligent Transportation Systems 17, 5 (2016), 1415--1427. Google ScholarDigital Library
- Min Tan, Yueming Wang, and Gang Pan. 2012. Feature reduction for efficient object detection via l1-norm latent SVM. In Sino-Foreign-Interchange Conference on Intelligent Science and Intelligent Data Engineering. 322--329. Google ScholarDigital Library
- Min Tan, Jun Yu, Qingming Huang, and Weichen Wu. 2018. Click data guided query modeling with click propagation and sparse coding. Multimedia Tools and Applications 3 (2018), 1--14. Google ScholarDigital Library
- Min Tan, Jun Yu, Zhou Yu, Fei Gao, Yong Rui, and Dacheng Tao. {n. d.}. User Click Data Based Fine-grained Image Recognition via Weakly Supervised Metric Learning. ACM Transactions on Multimedia Computing Communications and Applications (Accepted) ({n. d.}). Google ScholarDigital Library
- Min Tan, Jun Yu, Guangjian Zheng, Weichen Wu, and Kejia Sun. 2016. Deep Neural Network Boosted Large Scale Image Recognition Using User Click Data. In International Conference on Internet Multimedia Computing and Service. 118--121. Google ScholarDigital Library
- Weichen Wu, Min Tan, Guangjian Zheng, and Jun Yu. 2017. Query Modeling for Click Data Based Image Recognition Using Graph Based Propagation and Sparse Coding. In International Conference on Internet Multimedia Computing and Service. 191--199.Google Scholar
- Jianwei Yang, Devi Parikh, and Dhruv Batra. 2016. Joint Unsupervised Learning of Deep Representations and Image Clusters. In Computer Vision and Pattern Recognition. 5147--5156.Google Scholar
- Jun Yu, Yong Rui, and Bo Chen. 2013. Exploiting Click Constraints and Multi-view Features for Image Re-ranking. IEEE Transactions on Multimedia 16, 1 (2013), 159--168.Google ScholarCross Ref
- J. Yu, Y. Rui, and D. Tao. 2014. Click prediction for web image reranking using multimodal sparse coding. Image Processing IEEE Transactions on 23, 5 (2014), 2019--2032.Google ScholarCross Ref
- Guangjian Zheng, Min Tan, Jun Yu, Qing Wu, and Jianping Fan. 2017. Fine-grained image recognition via weakly supervised click data guided bilinear CNN model. In IEEE International Conference on Multimedia and Expo. 661--666.Google ScholarCross Ref
Index Terms
- Deep click feature based query merging for robust image recognition
Recommendations
Deep Neural Network Boosted Large Scale Image Recognition Using User Click Data
ICIMCS'16: Proceedings of the International Conference on Internet Multimedia Computing and ServiceRecognition by traditional visual features will result in a semantic gap. To bridge this gap, the user click data is employed recently. With this kind of data, images can be represented by the click feature vectors indicating their clicked queries. ...
Unsupervised local deep feature for image recognition
ULDF is proposed to make better use of autoencoder for image recognition. It is performed on local patches rather than whole images, which helps to scale the algorithm to realistic-sized images.Owning to the combination with BoW, it is more robust to ...
Efficient deep feature selection for remote sensing image recognition with fused deep learning architectures
AbstractConvolutional neural networks (CNNs) have recently emerged as a popular topic for machine learning in various academic and industrial fields. It is often an important problem to obtain a dataset with an appropriate size for CNN training. However, ...
Comments