Learning to Hash: A Guided Curriculum

From Foundations to Advanced Techniques in Hashing

Dive into the fascinating world of hashing with our guided curriculum designed for curious newcomers. Explore the foundations of hashing in machine learning, computer vision, and beyond, while gradually advancing to cutting-edge techniques and applications. Each track is crafted to engage and inspire, providing a clear path from basic concepts to advanced methodologies.

Foundational Concepts

Introduction to Hashing

Hashing is a technique that transforms data into a fixed-size string of characters. It is crucial for efficient data retrieval and storage. Understanding the basics of hashing sets the stage for exploring its applications in machine learning and computer vision.

Papers (6 top-engaged this week)
Videoclip: Contrastive Pre-training For Zero-shot Video-text Understanding
Videoclip: Contrastive Pre-training For Zero-shot Video-text Understanding
Hu Xu, Gargi Ghosh, Po-Yao Huang, et al. · 2021 · 343 citations
Mixvpr: Feature Mixing For Visual Place Recognition
Mixvpr: Feature Mixing For Visual Place Recognition
Amar Ali-Bey, Brahim Chaib-Draa, Philippe Giguère · 2023 · 226 citations
REGTR: End-to-end Point Cloud Correspondences With Transformers
REGTR: End-to-end Point Cloud Correspondences With Transformers
Zi Jian Yew, Gim Hee Lee · 2022 · 236 citations
Cross-batch Memory For Embedding Learning
Cross-batch Memory For Embedding Learning
Xun Wang, Haozhi Zhang, Weilin Huang, et al. · 2019 · 191 citations
Escape From Cells: Deep Kd-networks For The Recognition Of 3D Point Cloud Models
Escape From Cells: Deep Kd-networks For The Recognition Of 3D Point Cloud Models
Roman Klokov, Victor Lempitsky · 2017 · 758 citations
MVTN: Multi-view Transformation Network For 3D Shape Recognition
MVTN: Multi-view Transformation Network For 3D Shape Recognition
Abdullah Hamdi, Silvio Giancola, Bernard Ghanem · 2020 · 207 citations
Tutorials, tools, and deep dives

Supervised Hashing Basics

Supervised hashing leverages labeled data to learn hash functions that preserve the semantic similarity of data points. This concept is vital for tasks like image retrieval where accuracy is paramount. By understanding supervised hashing, you can improve retrieval performance significantly.

Papers (6 top-engaged this week)
Unsupervised Feature Learning Via Non-parametric Instance-level Discrimination
Unsupervised Feature Learning Via Non-parametric Instance-level Discrimination
Zhirong Wu, Yuanjun Xiong, Stella Yu, et al. · 2018 · 2635 citations
A Pose-sensitive Embedding For Person Re-identification With Expanded Cross Neighborhood Re-ranking
A Pose-sensitive Embedding For Person Re-identification With Expanded Cross Neighborhood Re-ranking
M. Saquib Sarfraz, Arne Schumann, Andreas Eberle, et al. · 2017 · 356 citations
Part-based Pseudo Label Refinement For Unsupervised Person Re-identification
Part-based Pseudo Label Refinement For Unsupervised Person Re-identification
Yoonki Cho, Woo Jae Kim, Seunghoon Hong, et al. · 2022 · 261 citations
Body Part-based Representation Learning For Occluded Person Re-identification
Body Part-based Representation Learning For Occluded Person Re-identification
Vladimir Somers, Christophe de Vleeschouwer, Alexandre Alahi · 2022 · 158 citations
Improving Person Re-identification By Attribute And Identity Learning
Improving Person Re-identification By Attribute And Identity Learning
Yutian Lin, Liang Zheng, Zhedong Zheng, et al. · 2017 · 576 citations
A Twofold Siamese Network For Real-time Object Tracking
A Twofold Siamese Network For Real-time Object Tracking
Anfeng He, Chong Luo, Xinmei Tian, et al. · 2018 · 540 citations
Tutorials, tools, and deep dives

Unsupervised Hashing Basics

Unsupervised hashing aims to learn hash functions without labeled data, relying instead on the inherent structure of the data. This approach is essential for large datasets where labeling is impractical, making it a key technique in modern machine learning.

Papers (6 top-engaged this week)
Unsupervised Feature Learning Via Non-parametric Instance-level Discrimination
Unsupervised Feature Learning Via Non-parametric Instance-level Discrimination
Zhirong Wu, Yuanjun Xiong, Stella Yu, et al. · 2018 · 2635 citations
Part-based Pseudo Label Refinement For Unsupervised Person Re-identification
Part-based Pseudo Label Refinement For Unsupervised Person Re-identification
Yoonki Cho, Woo Jae Kim, Seunghoon Hong, et al. · 2022 · 261 citations
Improving Person Re-identification By Attribute And Identity Learning
Improving Person Re-identification By Attribute And Identity Learning
Yutian Lin, Liang Zheng, Zhedong Zheng, et al. · 2017 · 576 citations
Interpretable And Generalizable Person Re-identification With Query-adaptive Convolution And Temporal Lifting
Interpretable And Generalizable Person Re-identification With Query-adaptive Convolution And Temporal Lifting
Shengcai Liao, Ling Shao · 2019 · 125 citations
Bsnet: Bi-similarity Network For Few-shot Fine-grained Image Classification
Bsnet: Bi-similarity Network For Few-shot Fine-grained Image Classification
Xiaoxu Li, Jijie Wu, Zhuo Sun, et al. · 2020 · 184 citations
A Discriminatively Learned CNN Embedding For Person Re-identification
A Discriminatively Learned CNN Embedding For Person Re-identification
Zhedong Zheng, Liang Zheng, Yi Yang · 2016 · 511 citations
Tutorials, tools, and deep dives

Introduction to Deep Hashing

Deep hashing integrates deep learning techniques with traditional hashing methods to improve performance in tasks like image retrieval. By leveraging neural networks, deep hashing can capture complex features, leading to more accurate and efficient retrieval systems.

Papers (6 top-engaged this week)
Videoclip: Contrastive Pre-training For Zero-shot Video-text Understanding
Videoclip: Contrastive Pre-training For Zero-shot Video-text Understanding
Hu Xu, Gargi Ghosh, Po-Yao Huang, et al. · 2021 · 343 citations
Mixvpr: Feature Mixing For Visual Place Recognition
Mixvpr: Feature Mixing For Visual Place Recognition
Amar Ali-Bey, Brahim Chaib-Draa, Philippe Giguère · 2023 · 226 citations
REGTR: End-to-end Point Cloud Correspondences With Transformers
REGTR: End-to-end Point Cloud Correspondences With Transformers
Zi Jian Yew, Gim Hee Lee · 2022 · 236 citations
Escape From Cells: Deep Kd-networks For The Recognition Of 3D Point Cloud Models
Escape From Cells: Deep Kd-networks For The Recognition Of 3D Point Cloud Models
Roman Klokov, Victor Lempitsky · 2017 · 758 citations
MVTN: Multi-view Transformation Network For 3D Shape Recognition
MVTN: Multi-view Transformation Network For 3D Shape Recognition
Abdullah Hamdi, Silvio Giancola, Bernard Ghanem · 2020 · 207 citations
O-CNN: Octree-based Convolutional Neural Networks For 3D Shape Analysis
O-CNN: Octree-based Convolutional Neural Networks For 3D Shape Analysis
Peng-Shuai Wang, Yang Liu, Yu-Xiao Guo, et al. · 2017 · 628 citations
Tutorials, tools, and deep dives

Intermediate Applications

Cross-Modal Hashing

Cross-modal hashing enables the retrieval of data across different modalities, such as images and text. This is particularly useful in applications like image-text matching, where understanding the relationship between different data types is essential.

Papers (6 top-engaged this week)
Videoclip: Contrastive Pre-training For Zero-shot Video-text Understanding
Videoclip: Contrastive Pre-training For Zero-shot Video-text Understanding
Hu Xu, Gargi Ghosh, Po-Yao Huang, et al. · 2021 · 343 citations
Massively Multilingual Sentence Embeddings For Zero-shot Cross-lingual Transfer And Beyond
Massively Multilingual Sentence Embeddings For Zero-shot Cross-lingual Transfer And Beyond
Mikel Artetxe, Holger Schwenk · 2018 · 362 citations
Medclip: Contrastive Learning From Unpaired Medical Images And Text
Medclip: Contrastive Learning From Unpaired Medical Images And Text
Zifeng Wang, Zhenbang Wu, Dinesh Agarwal, et al. · 2022 · 515 citations
Visual Semantic Reasoning For Image-text Matching
Visual Semantic Reasoning For Image-text Matching
Kunpeng Li, Yulun Zhang, Kai Li, et al. · 2019 · 502 citations
A Pose-sensitive Embedding For Person Re-identification With Expanded Cross Neighborhood Re-ranking
A Pose-sensitive Embedding For Person Re-identification With Expanded Cross Neighborhood Re-ranking
M. Saquib Sarfraz, Arne Schumann, Andreas Eberle, et al. · 2017 · 356 citations
Re-ranking Person Re-identification With K-reciprocal Encoding
Re-ranking Person Re-identification With K-reciprocal Encoding
Zhun Zhong, Liang Zheng, Donglin Cao, et al. · 2017 · 1199 citations
Tutorials, tools, and deep dives

Image Retrieval Methods

Image retrieval methods focus on efficiently finding images from large databases based on user queries. Understanding various image retrieval techniques, including feature extraction and hashing, is crucial for developing robust search systems.

Papers (6 top-engaged this week)
Large-scale Image Retrieval With Attentive Deep Local Features
Large-scale Image Retrieval With Attentive Deep Local Features
Hyeonwoo Noh, Andre Araujo, Jack Sim, et al. · 2016 · 602 citations
Unifying Deep Local And Global Features For Image Search
Unifying Deep Local And Global Features For Image Search
Bingyi Cao, Andre Araujo, Jack Sim · 2020 · 276 citations
Videoclip: Contrastive Pre-training For Zero-shot Video-text Understanding
Videoclip: Contrastive Pre-training For Zero-shot Video-text Understanding
Hu Xu, Gargi Ghosh, Po-Yao Huang, et al. · 2021 · 343 citations
Stacked Cross Attention For Image-text Matching
Stacked Cross Attention For Image-text Matching
Kuang-Huei Lee, Xi Chen, Gang Hua, et al. · 2018 · 923 citations
Massively Multilingual Sentence Embeddings For Zero-shot Cross-lingual Transfer And Beyond
Massively Multilingual Sentence Embeddings For Zero-shot Cross-lingual Transfer And Beyond
Mikel Artetxe, Holger Schwenk · 2018 · 362 citations
Medclip: Contrastive Learning From Unpaired Medical Images And Text
Medclip: Contrastive Learning From Unpaired Medical Images And Text
Zifeng Wang, Zhenbang Wu, Dinesh Agarwal, et al. · 2022 · 515 citations
Tutorials, tools, and deep dives

Advanced Techniques

Large-Scale Image Retrieval

Large-scale image retrieval focuses on efficiently searching and retrieving images from vast databases. Techniques like attentive deep local features and hierarchical structures are employed to enhance retrieval speed and accuracy.

Papers (6 top-engaged this week)
Videoclip: Contrastive Pre-training For Zero-shot Video-text Understanding
Videoclip: Contrastive Pre-training For Zero-shot Video-text Understanding
Hu Xu, Gargi Ghosh, Po-Yao Huang, et al. · 2021 · 343 citations
Re-ranking Person Re-identification With K-reciprocal Encoding
Re-ranking Person Re-identification With K-reciprocal Encoding
Zhun Zhong, Liang Zheng, Donglin Cao, et al. · 2017 · 1199 citations
Mixvpr: Feature Mixing For Visual Place Recognition
Mixvpr: Feature Mixing For Visual Place Recognition
Amar Ali-Bey, Brahim Chaib-Draa, Philippe Giguère · 2023 · 226 citations
REGTR: End-to-end Point Cloud Correspondences With Transformers
REGTR: End-to-end Point Cloud Correspondences With Transformers
Zi Jian Yew, Gim Hee Lee · 2022 · 236 citations
Escape From Cells: Deep Kd-networks For The Recognition Of 3D Point Cloud Models
Escape From Cells: Deep Kd-networks For The Recognition Of 3D Point Cloud Models
Roman Klokov, Victor Lempitsky · 2017 · 758 citations
MVTN: Multi-view Transformation Network For 3D Shape Recognition
MVTN: Multi-view Transformation Network For 3D Shape Recognition
Abdullah Hamdi, Silvio Giancola, Bernard Ghanem · 2020 · 207 citations
Tutorials, tools, and deep dives

Contrastive Learning for Hashing

Contrastive learning is a powerful technique that learns representations by contrasting positive and negative samples. This approach enhances the quality of hash functions, leading to improved performance in tasks like image-text matching and retrieval.

Papers (6 top-engaged this week)
Deep Image Retrieval: Learning Global Representations For Image Search
Deep Image Retrieval: Learning Global Representations For Image Search
Albert Gordo, Jon Almazan, Jerome Revaud, et al. · 2016 · 419 citations
Self-supervised Adversarial Hashing Networks For Cross-modal Retrieval
Self-supervised Adversarial Hashing Networks For Cross-modal Retrieval
Chao Li, Cheng Deng, Ning Li, et al. · 2018 · 405 citations
Auto-encoding Twin-bottleneck Hashing
Auto-encoding Twin-bottleneck Hashing
Yuming Shen, Jie Qin, Jiaxin Chen, et al. · 2020 · 113 citations
Local Feature Matching Using Deep Learning: A Survey
Local Feature Matching Using Deep Learning: A Survey
Shibiao Xu, Shunpeng Chen, Rongtao Xu, et al. · 2024 · 79 citations
Binary Generative Adversarial Networks For Image Retrieval
Binary Generative Adversarial Networks For Image Retrieval
Jingkuan Song · 2017 · 102 citations
A Decade Survey Of Content Based Image Retrieval Using Deep Learning
A Decade Survey Of Content Based Image Retrieval Using Deep Learning
Shiv Ram Dubey · 2020 · 277 citations
Tutorials, tools, and deep dives

Efficient Hashing Algorithms

Efficient hashing algorithms are essential for optimizing performance in large-scale systems. Understanding these algorithms allows for the development of systems that can handle vast amounts of data while maintaining quick access times.

Papers (6 top-engaged this week)
The Case For Learned Index Structures
The Case For Learned Index Structures
Tim Kraska, Alex Beutel, Ed H. Chi, et al. · 2017 · 629 citations
The Faiss Library
The Faiss Library
Matthijs Douze, Alexandr Guzhva, Chengqi Deng, et al. · 2024 · 293 citations
Dataset Discovery In Data Lakes
Dataset Discovery In Data Lakes
Alex Bogatu, Alvaro A. A. Fernandes, Norman W. Paton, et al. · 2020 · 108 citations
Vector Database Management Systems: Fundamental Concepts, Use-cases, And Current Challenges
Vector Database Management Systems: Fundamental Concepts, Use-cases, And Current Challenges
Toni Taipalus · 2023 · 78 citations
Revisiting The Inverted Indices For Billion-scale Approximate Nearest Neighbors
Revisiting The Inverted Indices For Billion-scale Approximate Nearest Neighbors
Dmitry Baranchuk, Artem Babenko, Yury Malkov · 2018 · 64 citations
A Comprehensive Survey on Vector Database: Storage and Retrieval Technique, Challenge
A Comprehensive Survey on Vector Database: Storage and Retrieval Technique, Challenge
Le Ma et al. · 2026
Tutorials, tools, and deep dives

Paper lists auto-refresh weekly from live engagement data. Last refresh: 2026-06-04.