Beyond Product Quantization: Deep Progressive Quantization for Image Retrieval

Abstract

Product Quantization (PQ) has long been a mainstream for generating an exponentially large codebook at very low memory/time cost. Despite its success, PQ is still tricky for the decomposition of high-dimensional vector space, and the retraining of model is usually unavoidable when the code length changes. In this work, we propose a deep progressive quantization (DPQ) model, as an alternative to PQ, for large scale image retrieval. DPQ learns the quantization codes sequentially and approximates the original feature space progressively. Therefore, we can train the quantization codes with different code lengths simultaneously. Specifically, we first utilize the label information for guiding the learning of visual features, and then apply several quantization blocks to progressively approach the visual features. Each quantization block is designed to be a layer of a convolutional neural network, and the whole framework can be trained in an end-to-end manner. Experimental results on the benchmark datasets show that our model significantly outperforms the state-of-the-art for image retrieval. Our model is trained once for different code lengths and therefore requires less computation time. Additional ablation study demonstrates the effect of each component of our proposed model. Our code is released at https://github.com/cfm-uestc/DPQ.

References in corpus (6)

• Simultaneous Feature Learning and Hash Coding with Deep Neural Networks
• Self-Supervised Video Hashing with Hierarchical Binary Auto-encoder
• Binary Voting with Delegable Proxy: An Analysis of Liquid Democracy
• Stacked Quantizers for Compositional Vector Compression
• Proxy Voting for Better Outcomes
• What Do We Elect Committees For? A Voting Committee Model for Multi-Winner Rules

Cited by in corpus (47)

• What Do We Want From Explainable Artificial Intelligence (XAI)? -- A Stakeholder Perspective on XAI and a Conceptual Model Guiding Interdisciplinary XAI Research
• Accelerating high-throughput virtual screening through molecular pool-based active learning
• Beyond Expertise and Roles: A Framework to Characterize the Stakeholders of Interpretable Machine Learning and their Needs
• Annotating Columns with Pre-trained Language Models
• Counterfactual State Explanations for Reinforcement Learning Agents via Generative Deep Learning
• Multiple Birds with One Stone: Beating $1/2$ for EFX and GMMS via Envy Cycle Elimination
• Forecast Network-Wide Traffic States for Multiple Steps Ahead: A Deep Learning Approach Considering Dynamic Non-Local Spatial Correlation and Non-Stationary Temporal Dependency
• Automating Data Science: Prospects and Challenges
• Comprehensible Artificial Intelligence on Knowledge Graphs: A survey
• Soloist: Generating Mixed-Initiative Tutorials from Existing Guitar Instructional Videos Through Audio Processing
• LMMS Reloaded: Transformer-based Sense Embeddings for Disambiguation and Beyond
• A Survey on Intent-aware Recommender Systems
• Empathetic Response Generation through Graph-based Multi-hop Reasoning on Emotional Causality
• Proactive Retrieval-based Chatbots based on Relevant Knowledge and Goals
• AEDNet: Adaptive Edge-Deleting Network For Subgraph Matching
• Unsupervised Social Event Detection via Hybrid Graph Contrastive Learning and Reinforced Incremental Clustering
• Sketching Robot Programs On the Fly
• Portrayal: Leveraging NLP and Visualization for Analyzing Fictional Characters
• A Survey of Source Code Representations for Machine Learning-Based Cybersecurity Tasks
• GripNet: Graph Information Propagation on Supergraph for Heterogeneous Graphs
• Cardinality Estimation over Knowledge Graphs with Embeddings and Graph Neural Networks
• Knowledge Graph Entity Alignment with Graph Convolutional Networks: Lessons Learned
• VAL: Interactive Task Learning with GPT Dialog Parsing
• Distantly Supervised Relation Extraction via Recursive Hierarchy-Interactive Attention and Entity-Order Perception
• A Local Method for Identifying Causal Relations under Markov Equivalence
• Robust Multimodal Sentiment Analysis of Image-Text Pairs by Distribution-Based Feature Recovery and Fusion
• Learning Attention-based Representations from Multiple Patterns for Relation Prediction in Knowledge Graphs
• Model-based inexact graph matching on top of CNNs for semantic scene understanding
• From the Fair Distribution of Predictions to the Fair Distribution of Social Goods: Evaluating the Impact of Fair Machine Learning on Long-Term Unemployment
• Making Intelligence: Ethical Values in IQ and ML Benchmarks
• Session-based Social and Dependency-aware Software Recommendation
• Deontic Paradoxes in ASP with Weak Constraints
• Exploring the Representational Power of Graph Autoencoder
• Predictive Modeling: BIM Command Recommendation Based on Large-scale Usage Logs
• Enhancing Function Name Prediction using Votes-Based Name Tokenization and Multi-Task Learning
• Blind Source Separation of Single-Channel Mixtures via Multi-Encoder Autoencoders
• Variational Prefix Tuning for Diverse and Accurate Code Summarization Using Pre-trained Language Models
• Formal Verification of Robustness and Resilience of Learning-Enabled State Estimation Systems
• Language as a Latent Sequence: deep latent variable models for semi-supervised paraphrase generation
• Fairness in Ranking under Disparate Uncertainty
• Backretrieval: An Image-Pivoted Evaluation Metric for Cross-Lingual Text Representations Without Parallel Corpora
• Semantic Graph Neural Network with Multi-measure Learning for Semi-supervised Classification
• A Contribution to the Defense of Liquid Democracy
• Towards Interactive Reinforcement Learning with Intrinsic Feedback
• Before It's Too Late: A State Space Model for the Early Prediction of Misinformation and Disinformation Engagement
• Self-adhesivity in lattices of abstract conditional independence models
• Reward Augmentation in Reinforcement Learning for Testing Distributed Systems