Explore the field of Learning to Hash with structure and clarity.
A visual, searchable map of key papers on hashing methods, ANN search, quantization, and vector indexing.
🔗 Live site: learning2hash.github.io
Learning to Hash is a foundational area in efficient similarity search, powering applications in large-scale retrieval, vision, and information systems.
But the literature is fragmented across subfields and venues. It’s hard to get a clear picture of the landscape.
Learning to Hash solves that by providing an interactive, structured interface to the field — with categories, tags, search, and taxonomy across modalities and methods.
- 📌 Taxonomy of methods: Binary hashing, deep hashing, quantization, indexing, multimodal
- 🔍 Search: Instantly find papers by title, authors, tags, or topics
- 🧠 Clustered tagging: Group papers by supervision level, modality, and algorithmic approach
- 🗂️ Categorized views: Hashing vs Quantization vs Indexing, clearly separated
- 🚫 No ads, no subscriptions — just structured research access
Visit: https://learning2hash.github.io
This site is statically hosted using GitHub Pages and built with:
- Python backend (for parsing arXiv data and generating markdown)
- Jekyll and JavaScript for the frontend
- YAML-based taxonomy and metadata files
All entries are manually curated and auto-generated from structured data.
Want to improve it or suggest new papers?
- Fork the repo
- Add a markdown file for the paper or update
taxonomy.yaml - Submit a pull request
You can also open an issue with suggestions or corrections — contributions are welcome!
If this project helps you:
- Give it a ⭐ on GitHub
- Share the site with others in the ANN / CV / ML community
- Suggest recent papers, tools, or ideas to include
This project is licensed under the GNU General Public License v3.0.
You may use, modify, and share this code, but any redistributed or derivative work must also be licensed under GPLv3.
See the LICENSE file for details.