Deep Hashing with Hash-Consistent Large Margin Proxy Embeddings

  title={Deep Hashing with Hash-Consistent Large Margin Proxy Embeddings},
  author={Pedro Morgado and Yunsheng Li and Jose Costa Pereira and Mohammad J. Saberian and Nuno Vasconcelos},
  journal={International Journal of Computer Vision},
Image hash codes are produced by binarizing the embeddings of convolutional neural networks (CNN) trained for either classification or retrieval. While proxy embeddings achieve good performance on both tasks, they are non-trivial to binarize, due to a rotational ambiguity that encourages non-binary embeddings. The use of a fixed set of proxies (weights of the CNN classification layer) is proposed to eliminate this ambiguity, and a procedure to design proxy sets that are nearly optimal for both… 
2 Citations
Concentrated hashing with neighborhood embedding for image retrieval and classification
A concentrated hashing method with neighborhood embedding (CHNE) for efficient and effective image retrieval and classification by integrating Cauchy cross-entropy and pair-wise weighted similarity loss and jointly minimize the regression quantization and neighborhood structure reconstruction errors in the loss function to improve the classification accuracy.


Supervised Learning of Semantics-Preserving Hash via Deep Convolutional Neural Networks
Compared with state-of-the-art approaches, SSDH achieves higher retrieval accuracy, while the classification performance is not sacrificed; yet it is effective and outperforms other hashing approaches on several benchmarks and large datasets.
Supervised hashing with kernels
A novel kernel-based supervised hashing model which requires a limited amount of supervised information, i.e., similar and dissimilar data pairs, and a feasible training cost in achieving high quality hashing, and significantly outperforms the state-of-the-arts in searching both metric distance neighbors and semantically similar neighbors is proposed.
Deep learning of binary hash codes for fast image retrieval
This work proposes an effective deep learning framework to generate binary hash codes for fast image retrieval by employing a hidden layer for representing the latent concepts that dominate the class labels in convolutional neural networks.
Deep Hashing Network for Efficient Similarity Retrieval
A novel Deep Hashing Network (DHN) architecture for supervised hashing is proposed, in which good image representation tailored to hash coding and formally control the quantization error are jointly learned.
Deep hashing learning networks
This paper proposes a supervised hashing learning method based on a well designed deep convolutional neural network, which tries to learn hashing code and compact representations of data simultaneously.
Simultaneous feature learning and hash coding with deep neural networks
Extensive evaluations on several benchmark image datasets show that the proposed simultaneous feature learning and hash coding pipeline brings substantial improvements over other state-of-the-art supervised or unsupervised hashing methods.
Deep Quantization Network for Efficient Image Retrieval
A novel Deep Quantization Network architecture for supervised hashing is proposed, which learns image representation for hash coding and formally control the quantization error and yields substantial boosts over latest state-of-the-art hashing methods.
Learning to Hash with Binary Reconstructive Embeddings
An algorithm for learning hash functions based on explicitly minimizing the reconstruction error between the original distances and the Hamming distances of the corresponding binary embeddings is developed.
Deep Supervised Hashing for Fast Image Retrieval
A novel Deep Supervised Hashing method to learn compact similarity-preserving binary code for the huge body of image data and extensive experiments show the promising performance of the method compared with the state-of-the-arts.
Deep Supervised Hashing with Triplet Labels
A triplet label based deep hashing method which aims to maximize the likelihood of the given triplet labels, which outperforms all the baselines on CIFAR-10 and NUS-WIDE datasets, including the state-of-the-art method DPSH.