Unsupervised Deep Hashing With Adaptive Feature Learning for Image Retrieval

The hashing method is widely used for large-scale image retrieval due to its low time and space complexity. However, the existing deep hashing methods are mainly designed for labeled datasets. Without supervised information, retrieval performance on unlabeled datasets is not guaranteed. In this letter, we propose a novel deep hashing approach for unsupervised image retrieval applications. The contributions are two-fold. First, the pseudolabels are generated using their global features aggregated from the pretrained network and employed as self-supervised information to optimize the objective function of training. Second, adaptive feature learning is used in this deep hashing framework to perform simultaneous hash function learning and global features learning in an unsupervised manner. The experimental results validated the effectiveness of the proposed method, obtaining state-of-the-art performances on several public datasets such as CIFAR-10, Holidays, and Oxford5k.

[1]  Tieniu Tan,et al.  Deep Supervised Discrete Hashing , 2017, NIPS.

[2]  Wei Liu,et al.  Supervised Discrete Hashing , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Antonio Torralba,et al.  Spectral Hashing , 2008, NIPS.

[4]  Wei Liu,et al.  Asymmetric Binary Coding for Image Search , 2017, IEEE Transactions on Multimedia.

[5]  Simon Osindero,et al.  Cross-Dimensional Weighting for Aggregated Deep Convolutional Features , 2015, ECCV Workshops.

[6]  David J. Fleet,et al.  Fast Exact Search in Hamming Space With Multi-Index Hashing , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Svetlana Lazebnik,et al.  Iterative quantization: A procrustean approach to learning binary codes , 2011, CVPR 2011.

[8]  Yi Shi,et al.  Deep Supervised Hashing with Triplet Labels , 2016, ACCV.

[9]  Jiwen Lu,et al.  Learning Compact Binary Descriptors with Unsupervised Deep Neural Networks , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Shih-Fu Chang,et al.  Semi-Supervised Hashing for Large-Scale Search , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Antonio Torralba,et al.  Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope , 2001, International Journal of Computer Vision.

[12]  Qi Tian,et al.  Feature representation for statistical-learning-based object detection: A review , 2015, Pattern Recognit..

[13]  Luo Si,et al.  Ranking Preserving Hashing for Fast Similarity Search , 2015, IJCAI.

[14]  Jian Yang,et al.  Discriminative Deep Quantization Hashing for Face Image Retrieval , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[15]  Michael Isard,et al.  Object retrieval with large vocabularies and fast spatial matching , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[16]  Michael Isard,et al.  Lost in quantization: Improving particular object retrieval in large scale image databases , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[17]  Deng Cai,et al.  Density Sensitive Hashing , 2012, IEEE Transactions on Cybernetics.

[18]  Cordelia Schmid,et al.  Hamming Embedding and Weak Geometric Consistency for Large Scale Image Search , 2008, ECCV.

[19]  Heng Tao Shen,et al.  Unsupervised Deep Hashing with Similarity-Adaptive and Discrete Optimization , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[21]  Ngai-Man Cheung,et al.  Simultaneous Feature Aggregating and Hashing for Large-Scale Image Search , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Jing Wang,et al.  Video Hashing Algorithm With Weighted Matching Based on Visual Saliency , 2012, IEEE Signal Processing Letters.

[23]  Jian Sun,et al.  K-Means Hashing: An Affinity-Preserving Quantization Method for Learning Binary Compact Codes , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[24]  Piotr Indyk,et al.  Similarity Search in High Dimensions via Hashing , 1999, VLDB.

[25]  Qi Tian,et al.  A survey of recent advances in visual feature detection , 2015, Neurocomputing.

[26]  Moses Charikar,et al.  Similarity estimation techniques from rounding algorithms , 2002, STOC '02.

[27]  Cordelia Schmid,et al.  Improving Bag-of-Features for Large Scale Image Search , 2010, International Journal of Computer Vision.

[28]  Kristen Grauman,et al.  Kernelized locality-sensitive hashing for scalable image search , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[29]  Ling Shao,et al.  Unsupervised Deep Hashing With Pseudo Labels for Scalable Image Retrieval , 2018, IEEE Transactions on Image Processing.

[30]  Wu-Jun Li,et al.  Feature Learning Based Deep Supervised Hashing with Pairwise Labels , 2015, IJCAI.

[31]  Yang Yang,et al.  A Fast Optimization Method for General Binary Code Learning , 2016, IEEE Transactions on Image Processing.

[32]  Jinhui Tang,et al.  Weakly Supervised Multimodal Hashing for Scalable Social Image Retrieval , 2018, IEEE Transactions on Circuits and Systems for Video Technology.

[33]  Chu-Song Chen,et al.  Supervised Learning of Semantics-Preserving Hash via Deep Convolutional Neural Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[34]  Yang Yang,et al.  Deep Asymmetric Pairwise Hashing , 2017, ACM Multimedia.

[35]  Wu-Jun Li,et al.  Scalable Graph Hashing with Feature Transformation , 2015, IJCAI.

[36]  Ping Wang,et al.  Robust Image Hashing Based on Selective Quaternion Invariance , 2015, IEEE Signal Processing Letters.