Bit-Scalable Deep Hashing With Regularized Similarity Learning for Image Retrieval and Person Re-Identification
Top Cited Papers
- 11 August 2015
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 24 (12), 4766-4779
- https://doi.org/10.1109/tip.2015.2467315
Abstract
Extracting informative image features and learning effective approximate hashing functions are two crucial steps in image retrieval. Conventional methods often study these two steps separately, e.g., learning hash functions from a predefined hand-crafted feature space. Meanwhile, the bit lengths of output hashing codes are preset in the most previous methods, neglecting the significance level of different bits and restricting their practical flexibility. To address these issues, we propose a supervised learning framework to generate compact and bit-scalable hashing codes directly from raw images. We pose hashing learning as a problem of regularized similarity learning. In particular, we organize the training images into a batch of triplet samples, each sample containing two images with the same label and one with a different label. With these triplet samples, we maximize the margin between the matched pairs and the mismatched pairs in the Hamming space. In addition, a regularization term is introduced to enforce the adjacency consistency, i.e., images of similar appearances should have similar codes. The deep convolutional neural network is utilized to train the model in an end-to-end fashion, where discriminative image features and hash functions are simultaneously optimized. Furthermore, each bit of our hashing codes is unequally weighted, so that we can manipulate the code lengths by truncating the insignificant bits. Our framework outperforms state-of-the-arts on public benchmarks of similar image search and also achieves promising results in the application of person re-identification in surveillance. It is also shown that the generated bit-scalable hashing codes well preserve the discriminative powers with shorter code lengths.Keywords
Other Versions
Funding Information
- Hong Kong Scholar Program
- Guangdong Natural Science Foundation (S2013050014548, 2014A030313201)
- Program of Guangzhou Zhujiang Star of Science and Technology (2013J2200067)
This publication has 22 references indexed in Scilit:
- Deep feature learning with relative distance comparison for person re-identificationPattern Recognition, 2015
- PISA: Pixelwise Image Saliency by Aggregating Complementary Appearance Contrast Measures With Edge-Preserving CoherenceIEEE Transactions on Image Processing, 2015
- Discriminatively Trained And-Or Graph Models for Object Shape DetectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- DeepReID: Deep Filter Pairing Neural Network for Person Re-identificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Rich Feature Hierarchies for Accurate Object Detection and Semantic SegmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Submodular video hashingPublished by Association for Computing Machinery (ACM) ,2012
- Fast computation of min-Hash signatures for image collectionsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- Laplacian Sparse Coding, Hypergraph Laplacian Sparse Coding, and ApplicationsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- 3D Convolutional Neural Networks for Human Action RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- Iterative quantization: A procrustean approach to learning binary codesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011