ABSTRACT
Instance search aims at retrieving images containing a particular query instance. Recently, image features derived from pre-trained convolutional neural networks (CNNs) have been shown to provide promising performance for image retrieval. However, the robustness of these features is still limited by hard positives and hard negatives. To address this issue, this work focuses on reconstructing a new representation based on conventional CNN features to capture the intrinsic image manifold in the original feature space. After the feature reconstruction, the Euclidean distance can be applied in the new space to measure the pairwise distance among feature points. The proposed method is highly efficient, which benefits from the linear search complexity and a further optimization for speedup. Experiments demonstrate that our method achieves promising efficiency with highly competitive accuracy. This work succeeds in capturing implicit embedding information in images as well as reducing the computational complexity significantly.
- Hossein Azizpour, Ali Sharif Razavian, Josephine Sullivan, Atsuto Maki, and Stefan Carlsson. 2015. From generic to specific deep representations for visual recognition 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops, Boston, MA, USA, June 7-12, 2015. 36--45.Google Scholar
- Artem Babenko and Victor S. Lempitsky. 2015. Aggregating Deep Convolutional Features for Image Retrieval. CoRR Vol. abs/1510.07493 (2015). http://arxiv.org/abs/1510.07493Google Scholar
- Mikhail Belkin and Partha Niyogi. 2001. Laplacian Eigenmaps and Spectral Techniques for Embedding and Clustering Advances in Neural Information Processing Systems 14 {Neural Information Processing Systems: Natural and Synthetic, NIPS 2001, December 3-8, 2001, Vancouver, British Columbia, Canada}. 585--591. Google ScholarDigital Library
- Jie Chen, Jie Shao, Fumin Shen, Chengkun He, Lianli Gao, and Heng Tao Shen. 2017. Movie Fill in the Blank with Adaptive Temporal Attention and Description Update Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, CIKM 2017, Singapore, November 06- 10, 2017. 1039--1048. Google ScholarDigital Library
- Nello Cristianini, John Shawe-Taylor, and Jaz S. Kandola. 2001. Spectral Kernel Methods for Clustering. In Advances in Neural Information Processing Systems 14 {Neural Information Processing Systems: Natural and Synthetic, NIPS 2001, December 3-8, 2001, Vancouver, British Columbia, Canada}. 649--655. Google ScholarDigital Library
- Lianli Gao, Tao He, Jingkuan Song, Xing Xu, and Heng Tao Shen. 2018. Deep Region Hashing for Efficient Large-scale Instance Search from Images Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, February 2-7, 2018, New Orleans, Louisiana, USA.Google Scholar
- Spyros Gidaris and Nikos Komodakis. 2016. LocNet: Improving Localization Accuracy for Object Detection 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, June 27-30, 2016. 789--798.Google Scholar
- Bharath Hariharan, Pablo Andrés Arbeláez, Ross B. Girshick, and Jitendra Malik. 2015. Hypercolumns for object segmentation and fine-grained localization IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, MA, USA, June 7-12, 2015. 447--456.Google Scholar
- Ahmet Iscen, Yannis S. Avrithis, Giorgos Tolias, Teddy Furon, and Ondrej Chum. 2017 a. Fast Spectral Ranking for Similarity Search. CoRR Vol. abs/1703.06935 (2017). http://arxiv.org/abs/1703.06935Google Scholar
- Ahmet Iscen, Giorgos Tolias, Yannis S. Avrithis, Teddy Furon, and Ondrej Chum. 2017 b. Efficient Diffusion on Region Manifolds: Recovering Small Objects with Compact CNN Representations. In 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, Hawaii, USA, July 22-25, 2017. 2077--2086.Google Scholar
- Jie Lin, Olivier Morère, Antoine Veillard, Ling-Yu Duan, Hanlin Goh, and Vijay Chandrasekhar. 2017. DeepHash for Image Instance Retrieval: Getting Regularization, Depth and Fine-Tuning Right. In Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval, ICMR 2017, Bucharest, Romania, June 6-9, 2017. 133--141. Google ScholarDigital Library
- Canyi Lu, Shuicheng Yan, and Zhouchen Lin. 2016. Convex Sparse Spectral Clustering: Single-View to Multi-View. IEEE Trans. Image Processing Vol. 25, 6 (2016), 2833--2843. Google ScholarDigital Library
- Eva Mohedano, Kevin McGuinness, Noel E. O'Connor, Amaia Salvador, Ferran Marqués, and Xavier Giró i Nieto. 2016. Bags of Local Convolutional Features for Scalable Instance Search Proceedings of the 2016 ACM on International Conference on Multimedia Retrieval, ICMR 2016, New York, New York, USA, June 6--9, 2016. 327--331. Google ScholarDigital Library
- Hyeonwoo Noh, Seunghoon Hong, and Bohyung Han. 2015. Learning Deconvolution Network for Semantic Segmentation 2015 IEEE International Conference on Computer Vision, ICCV 2015, Santiago, Chile, December 7-13, 2015. 1520--1528. Google ScholarDigital Library
- James Philbin, Ondrej Chum, Michael Isard, Josef Sivic, and Andrew Zisserman. 2007. Object retrieval with large vocabularies and fast spatial matching 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2007), 18--23 June 2007, Minneapolis, Minnesota, USA.Google Scholar
- James Philbin, Ondrej Chum, Michael Isard, Josef Sivic, and Andrew Zisserman. 2008. Lost in quantization: Improving particular object retrieval in large scale image databases 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2008), 24--26 June 2008, Anchorage, Alaska, USA.Google Scholar
- Danfeng Qin, Stephan Gammeter, Lukas Bossard, Till Quack, and Luc J. Van Gool. 2011. Hello neighbor: Accurate object retrieval with k-reciprocal nearest neighbors The 24th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011, Colorado Springs, CO, USA, 20--25 June 2011. 777--784. Google ScholarDigital Library
- Filip Radenovic, Giorgos Tolias, and Ondrej Chum. 2016. CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples Computer Vision - ECCV 2016 - 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part I. 3--20.Google Scholar
- Ali Sharif Razavian, Josephine Sullivan, Stefan Carlsson, and Atsuto Maki. 2016. Visual Instance Retrieval with Deep Convolutional Networks. ITE Transactions on Media Technology and Applications Vol. 4, 3 (2016), 251--258.Google ScholarCross Ref
- Shaoqing Ren, Kaiming He, Ross B. Girshick, and Jian Sun. 2017. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Trans. Pattern Anal. Mach. Intell. Vol. 39, 6 (2017), 1137--1149. Google ScholarDigital Library
- Sam T. Roweis, and Lawrence K. Saul. 2000. Nonlinear Dimensionality Reduction by Locally Linear Embedding. Science Vol. 290, 5500 (2000), 2323--2326.Google ScholarCross Ref
- Evan Shelhamer, Jonathan Long, and Trevor Darrell. 2017. Fully Convolutional Networks for Semantic Segmentation. IEEE Trans. Pattern Anal. Mach. Intell. Vol. 39, 4 (2017), 640--651. Google ScholarDigital Library
- Joshua B. Tenenbaum, Vin de Silva, and John C. Langford. 2000. A Global Geometric Framework for Nonlinear Dimensionality Reduction. Science Vol. 290, 5500 (2000), 2319--2323.Google ScholarCross Ref
- Giorgos Tolias, Ronan Sicre, and Hervé Jégou. 2015. Particular object retrieval with integral max-pooling of CNN activations. CoRR Vol. abs/1511.05879 (2015). http://arxiv.org/abs/1511.05879 tempurlGoogle Scholar
- Bo Wang, Jie Shao, Chengkun He, Gang Hu, and Xing Xu. 2017. Spatial Verification via Compact Words for Mobile Instance Search MultiMedia Modeling - 23rd International Conference, MMM 2017, Reykjavik, Iceland, January 4-6, 2017, Proceedings, Part II. 356--367.Google Scholar
- Kilian Q. Weinberger and Lawrence K. Saul. 2006. An Introduction to Nonlinear Dimensionality Reduction by Maximum Variance Unfolding. In Proceedings, The Twenty-First National Conference on Artificial Intelligence and the Eighteenth Innovative Applications of Artificial Intelligence Conference, July 16--20, 2006, Boston, Massachusetts, USA. 1683--1686. Google ScholarDigital Library
- Tan Yu, Yuwei Wu, Sreyasee Das Bhattacharjee, and Junsong Yuan. 2017. Efficient Object Instance Search Using Fuzzy Objects Matching Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, February 4-9, 2017, San Francisco, California, USA. 4320--4326.Google Scholar
Index Terms
- Feature Reconstruction by Laplacian Eigenmaps for Efficient Instance Search
Recommendations
Local linear Laplacian eigenmaps
We have derived local linear Laplacian eigenmaps (LLLE) a manifold learning algorithm.The LLLE finds multiple local linear structures.The LLLE used P artificial neighbors to construct the adjacency graph.The experimental results indicate that it can ...
Incremental Laplacian eigenmaps by preserving adjacent information between data points
Traditional nonlinear manifold learning methods have achieved great success in dimensionality reduction and feature extraction, most of which are batch modes. However, if new samples are observed, the batch methods need to be calculated repeatedly, ...
Component preserving laplacian eigenmaps for data reconstruction and dimensionality reduction
AbstractLaplacian Eigenmaps (LE) is a widely used dimensionality reduction and data reconstruction method. When the data has multiple connected components, the LE method has two obvious deficiencies. First, it might reconstruct each component as a single ...
Comments