Generalized Product Quantization Network for Semi-Supervised Image Retrieval

  title={Generalized Product Quantization Network for Semi-Supervised Image Retrieval},
  author={Young Kyun Jang and Nam Ik Cho},
  journal={2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  • Young Kyun Jang, N. Cho
  • Published 2020
  • Computer Science
  • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Image retrieval methods that employ hashing or vector quantization have achieved great success by taking advantage of deep learning. However, these approaches do not meet expectations unless expensive label information is sufficient. To resolve this issue, we propose the first quantization-based semi-supervised image retrieval scheme: Generalized Product Quantization (GPQ) network. We design a novel metric learning strategy that preserves semantic similarity between labeled data, and employ… Expand
Open-Set Representation Learning through Combinatorial Embedding
This work proposes a combinatorial learning approach, which naturally clusters the examples in unseen classes using the compositional knowledge given by multiple supervised meta-classifiers on heterogeneous label spaces, and introduces a metric learning strategy to estimate pairwise pseudo-labels for improving representations of unlabeled examples. Expand
Orthonormal Product Quantization Network for Scalable Face Image Retrieval
This paper makes the first attempt to integrate product quantization into an end-to-end deep learning framework for face image retrieval with a novel scheme using predefined orthonormal vectors as codewords using a fixed 90-degree angular separation. Expand
More Photos are All You Need: Semi-Supervised Learning for Fine-Grained Sketch Based Image Retrieval
This paper introduces a novel semi-supervised framework for cross-modal retrieval that can additionally leverage large-scale unlabelled photos to account for data scarcity, and treats generation and retrieval as two conjugate problems, where a joint learning procedure is devised for each module to mutually benefit from each other. Expand
Multi-focus image fusion based on nonsubsampled contourlet transform and residual removal
A novel multi-focus image fusion method which can effectively bridge the gap between the transform domain and spatial domain based methods is proposed, which outperforms some state-of-the-art methods in both quantitative and qualitative evaluations. Expand
Refining Pseudo Labels with Clustering Consensus over Generations for Unsupervised Object Re-identification
This work proposes to properly estimate pseudo label similarities between consecutive training generations with clustering consensus and refine pseudo labels with temporally propagated and ensembled pseudo labels to improve classification with dynamically changing classes over generations. Expand
Self-supervised Product Quantization for Deep Unsupervised Image Retrieval
  • Young Kyun Jang, N. Cho
  • Computer Science
  • ArXiv
  • 2021
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. Expand
Similarity Guided Deep Face Image Retrieval
This paper attempts to improve the face image retrieval quality by proposing a Similarity Guided Hashing (SGH) method, which gently considers self and pairwise-similarity simultaneously and employs various data augmentations designed to explore elaborate similarities between face images. Expand


NUS-WIDE: a real-world web image database from National University of Singapore
The benchmark results indicate that it is possible to learn effective models from sufficiently large image dataset to facilitate general image retrieval and four research issues on web image annotation and retrieval are identified. Expand
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
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. Expand
Deep Triplet Quantization
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. Expand
Product Quantization Network for Fast Image Retrieval
Through the proposed product quantization network, the author can obtain a discriminative and compact image representation in an end-to-end manner, which further enables a fast and accurate image retrieval. Expand
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. Expand
Semi-supervised Generative Adversarial Hashing for Image Retrieval
This paper unify a generative model, a discriminative model and a deep hashing model in a framework for making use of triplet-wise information and unlabeled data, and proposes a semi-supervised ranking loss and an adversary ranking loss to learn binary codes which preserve semantic similarity for both labeled data and unl labeled data. Expand
Semi-Supervised Deep Hashing with a Bipartite Graph
A novel semi-supervised hashing method for image retrieval, named Deep Hashing with a Bipartite Graph (BGDH), to simultaneously learn embeddings, features and hash codes, which outperforms state-of-the-art hashing methods. Expand
SuBiC: A Supervised, Structured Binary Code for Image Search
This work proposes herein a novel method to make deep convolutional neural networks produce supervised, compact, structured binary codes for visual search that outperforms state-of-the-art compact representations based on deep hashing or structured quantization in single and cross-domain category retrieval, instance retrieval and classification. Expand
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. Expand
Supervised Discrete Hashing
This work proposes a new supervised hashing framework, where the learning objective is to generate the optimal binary hash codes for linear classification, and introduces an auxiliary variable to reformulate the objective such that it can be solved substantially efficiently by employing a regularization algorithm. Expand