# Auto-Encoding Twin-Bottleneck Hashing

arXiv: https://arxiv.org/abs/2002.11930 · HTML: https://mlsanity.com/paper/2002.11930/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Feb 2020.

## Built on by (most cited first, 26 of 26)

- [Self-supervised Product Quantization for Deep Unsupervised Image Retrieval](https://mlsanity.com/paper/2109.02244/) (2021)
- [Unsupervised Hashing with Contrastive Information Bottleneck](https://mlsanity.com/paper/2105.06138/) (2021)
- [Contrastive Quantization with Code Memory for Unsupervised Image Retrieval](https://mlsanity.com/paper/2109.05205/) (2021)
- [COMAE: COMprehensive Attribute Exploration for Zero-shot Hashing](https://mlsanity.com/paper/2402.16424/) (2024)
- [Dynamic Weighted Combiner for Mixed-Modal Image Retrieval](https://mlsanity.com/paper/2312.06179/) (2023)
- [Deep Hash Distillation for Image Retrieval](https://mlsanity.com/paper/2112.08816/) (2021)
- [Hyperbolic Hierarchical Contrastive Hashing](https://mlsanity.com/paper/2212.08904/) (2022)
- [Semi-supervised Network Embedding with Differentiable Deep Quantisation](https://mlsanity.com/paper/2108.09128/) (2021)
- [Language Guided Local Infiltration for Interactive Image Retrieval](https://mlsanity.com/paper/2304.07747/) (2023)
- [NeuroHash: A Hyperdimensional Neuro-Symbolic Framework for Spatially-Aware Image Hashing and Retrieval](https://mlsanity.com/paper/2404.11025/) (2024)
- [Unsupervised Hashing with Semantic Concept Mining](https://mlsanity.com/paper/2209.11475/) (2022)
- [ViT2Hash: Unsupervised Information-Preserving Hashing](https://mlsanity.com/paper/2201.05541/) (2022)
- [Learning to Hash Naturally Sorts](https://mlsanity.com/paper/2201.13322/) (2022)
- [Dual-Stream Knowledge-Preserving Hashing for Unsupervised Video Retrieval](https://mlsanity.com/paper/2310.08009/) (2023)
- [Deep Self-Adaptive Hashing for Image Retrieval](https://mlsanity.com/paper/2108.07094/) (2021)
- [Vision Transformer Based Video Hashing Retrieval for Tracing the Source of Fake Videos](https://mlsanity.com/paper/2112.08117/) (2021)
- [Unsupervised Hashing with Similarity Distribution Calibration](https://mlsanity.com/paper/2302.07669/) (2023)
- [Similarity Guided Deep Face Image Retrieval](https://mlsanity.com/paper/2107.05025/) (2021)
- [Weighted Contrastive Hashing](https://mlsanity.com/paper/2209.14099/) (2022)
- [Torsion Graph Neural Networks](https://mlsanity.com/paper/2306.13541/) (2023)
- [From Image Hashing to Scene Change Detection](https://mlsanity.com/paper/2605.12259/) (2026)
- [Deep Unsupervised Hashing with Latent Semantic Components](https://mlsanity.com/paper/2203.09420/) (2022)
- [Supervised Auto-Encoding Twin-Bottleneck Hashing](https://mlsanity.com/paper/2306.11122/) (2023)
- [Transformer-based Clipped Contrastive Quantization Learning for Unsupervised Image Retrieval](https://mlsanity.com/paper/2401.15362/) (2024)
- [Bit-mask Robust Contrastive Knowledge Distillation for Unsupervised Semantic Hashing](https://mlsanity.com/paper/2403.06071/) (2024)
- [NeuRoute: Logit-Guided Neural Routing for Billion-Scale Vector Search with Sub-Hour Index Construction](https://mlsanity.com/paper/2608.15438/) (2026)

## Abstract (arXiv)

Conventional unsupervised hashing methods usually take advantage of similarity graphs, which are either pre-computed in the high-dimensional space or obtained from random anchor points. On the one hand, existing methods uncouple the procedures of hash function learning and graph construction. On the other hand, graphs empirically built upon original data could introduce biased prior knowledge of data relevance, leading to sub-optimal retrieval performance. In this paper, we tackle the above problems by proposing an efficient and adaptive code-driven graph, which is updated by decoding in the context of an auto-encoder. Specifically, we introduce into our framework twin bottlenecks (i.e., latent variables) that exchange crucial information collaboratively. One bottleneck (i.e., binary codes) conveys the high-level intrinsic data structure captured by the code-driven graph to the other (i.e., continuous variables for low-level detail information), which in turn propagates the updated network feedback for the encoder to learn more discriminative binary codes. The auto-encoding learning objective literally rewards the code-driven graph to learn an optimal encoder. Moreover, the proposed model can be simply optimized by gradient descent without violating the binary constraints. Experiments on benchmarked datasets clearly show the superiority of our framework over the state-of-the-art hashing methods. Our source code can be found at https://github.com/ymcidence/TBH.