SuBiC: A Supervised, Structured Binary Code for Image Search

@article{Jain2017SuBiCAS,
  title={SuBiC: A Supervised, Structured Binary Code for Image Search},
  author={Himalaya Jain and Joaquin Zepeda and Patrick P{\'e}rez and R{\'e}mi Gribonval},
  journal={2017 IEEE International Conference on Computer Vision (ICCV)},
  year={2017},
  pages={833-842}
}
For large-scale visual search, highly compressed yet meaningful representations of images are essential. Structured vector quantizers based on product quantization and its variants are usually employed to achieve such compression while minimizing the loss of accuracy. Yet, unlike binary hashing schemes, these unsupervised methods have not yet benefited from the supervision, end-to-end learning and novel architectures ushered in by the deep learning revolution. We hence propose herein a novel… 

Figures and Tables from this paper

Unsupervised Neural Quantization for Compressed-Domain Similarity Search
TLDR
This paper introduces a DNN architecture for the unsupervised compressed-domain retrieval, based on multi-codebook quantization, and demonstrates the exceptional advantage of the scheme over existing quantization approaches on several datasets of visual descriptors via outperforming the previous state-of-the-art by a large margin.
Self-supervised Product Quantization for Deep Unsupervised Image Retrieval
  • Young Kyun Jang, N. Cho
  • Computer Science
    2021 IEEE/CVF International Conference on Computer Vision (ICCV)
  • 2021
TLDR
This work proposes the first deep unsupervised image retrieval method dubbed SPQ, which is label-free and trained in a self-supervised manner, and designs a Cross Quantized Contrastive learning strategy that jointly learns codewords and deep visual descriptors by comparing individually transformed images.
Deep Spherical Quantization for Image Search
TLDR
Deep Spherical Quantization (DSQ) is put forward, a novel method to make deep convolutional neural networks generate supervised and compact binary codes for efficient image search and an easy-to-implement extension of the quantization technique that enforces sparsity on the codebooks is introduced.
End-To-End Supervised Product Quantization for Image Search and Retrieval
  • Benjamin Klein, Lior Wolf
  • Computer Science
    2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2019
TLDR
To the knowledge, this is the first work to introduce a dictionary-based representation that is inspired by Product Quantization and which is learned end-to-end, and thus benefits from the supervised signal.
Deep TripletQuantization
TLDR
Deep Triplet Quantization (DTQ), a novel approach to learning deep quantization models from the similarity triplets, can generate high-quality and compact binary codes, which yields state-of-the-art image retrieval performance on three benchmark datasets, NUS-WIDE, CIFAR-10, and MS-COCO.
Learning Effective Binary Visual Representations with Deep Networks
TLDR
This paper proposes Approximately Binary Clamping (ABC), which is non-saturating, end-to-end trainable, with fast convergence and can output true binary visual representations, which achieves comparable accuracy in ImageNet classification as its real-valued counterpart, and even generalizes better in object detection.
Deep Product Quantization Module for Efficient Image Retrieval
TLDR
A simple but effective deep Product Quantization Module (PQM) to jointly learn discriminative codebook and precise hard assignment in an end-to-end manner and a reconstruction loss to minimize the domain gap between the original embedding features and codebook is proposed.
Multiple Exemplars Learning for Fast Image Retrieval
TLDR
This work proposes MEL loss which trains the network in a considerably more efficient manner than existing deep product quantization approaches based on pairwise or triplet loss, and incorporates the proposed MEL in a convolutional neural network, supporting end-to-end training.
Deep Triplet Quantization
TLDR
Deep Triplet Quantization (DTQ), a novel approach to learning deep quantization models from the similarity triplets, can generate high-quality and compact binary codes, which yields state-of-the-art image retrieval performance on three benchmark datasets, NUS-WIDE, CIFAR-10, and MS-COCO.
Generalized Product Quantization Network for Semi-supervised Hashing
TLDR
This work proposes the first quantization-based semi-supervised hashing scheme: Generalized Product Quantization (GPQ) network, which designs a novel metric learning strategy that preserves semantic similarity between labeled data, and employs entropy regularization term to fully exploit inherent potentials of unlabeled data.
...
...

References

SHOWING 1-10 OF 48 REFERENCES
Deep Supervised Hashing for Fast Image Retrieval
TLDR
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 learning of binary hash codes for fast image retrieval
TLDR
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.
Simultaneous feature learning and hash coding with deep neural networks
TLDR
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
TLDR
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.
Deep Image Retrieval: Learning Global Representations for Image Search
TLDR
This work proposes a novel approach for instance-level image retrieval that produces a global and compact fixed-length representation for each image by aggregating many region-wise descriptors by leveraging a ranking framework and projection weights to build the region features.
Bit-Scalable Deep Hashing With Regularized Similarity Learning for Image Retrieval and Person Re-Identification
TLDR
A supervised learning framework to generate compact and bit-scalable hashing codes directly from raw images that outperforms state-of-the-arts on public benchmarks of similar image search and achieves promising results in the application of person re-identification in surveillance.
Supervised hashing with kernels
TLDR
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 semantic ranking based hashing for multi-label image retrieval
TLDR
In this work, deep convolutional neural network is incorporated into hash functions to jointly learn feature representations and mappings from them to hash codes, which avoids the limitation of semantic representation power of hand-crafted features.
Indexing of the CNN features for the large scale image search
TLDR
A novel indexing framework that combines inverted table and hashing codes is proposed, which is faster than the reformed inverted tables with the introduced strategies and provides fair comparison between popular CNN features.
Neural Codes for Image Retrieval
TLDR
A thorough discussion of several state-of-the-art techniques in image retrieval by considering the associated subproblems: image description, descriptor compression, nearest-neighbor search and query expansion, and the combined use of deep architectures and hand-crafted image representations for accurate and efficient image retrieval.
...
...