# HashNet: Deep Learning to Hash by Continuation

arXiv: https://arxiv.org/abs/1702.00758 · HTML: https://mlsanity.com/paper/1702.00758/

## Key facts

- Cited by 122 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Feb 2017.

## Built on by (most cited first, 30 of 122)

- [The Faiss library](https://mlsanity.com/paper/2401.08281/) (2024)
- [MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement](https://mlsanity.com/paper/2104.03538/) (2021)
- [Efficient Passage Retrieval with Hashing for Open-domain Question Answering](https://mlsanity.com/paper/2106.00882/) (2021)
- [PastNet: Introducing Physical Inductive Biases for Spatio-temporal Video Prediction](https://mlsanity.com/paper/2305.11421/) (2023)
- [One Loss for All: Deep Hashing with a Single Cosine Similarity based Learning Objective](https://mlsanity.com/paper/2109.14449/) (2021)
- [RepMix: Representation Mixing for Robust Attribution of Synthesized Images](https://mlsanity.com/paper/2207.02063/) (2022)
- [Self-supervised Product Quantization for Deep Unsupervised Image Retrieval](https://mlsanity.com/paper/2109.02244/) (2021)
- [BadHash: Invisible Backdoor Attacks against Deep Hashing with Clean Label](https://mlsanity.com/paper/2207.00278/) (2022)
- [Unsupervised Hashing with Contrastive Information Bottleneck](https://mlsanity.com/paper/2105.06138/) (2021)
- [Prototypical Hash Encoding for On-the-Fly Fine-Grained Category Discovery](https://mlsanity.com/paper/2410.19213/) (2024)
- [A Survey for Efficient Open Domain Question Answering](https://mlsanity.com/paper/2211.07886/) (2022)
- [Hash3D: Training-free Acceleration for 3D Generation](https://mlsanity.com/paper/2404.06091/) (2024)
- [DnS: Distill-and-Select for Efficient and Accurate Video Indexing and Retrieval](https://mlsanity.com/paper/2106.13266/) (2021)
- [Continual Learning for Visual Search with Backward Consistent Feature Embedding](https://mlsanity.com/paper/2205.13384/) (2022)
- [COMAE: COMprehensive Attribute Exploration for Zero-shot Hashing](https://mlsanity.com/paper/2402.16424/) (2024)
- [OSCAR-Net: Object-centric Scene Graph Attention for Image Attribution](https://mlsanity.com/paper/2108.03541/) (2021)
- [Backdoor Attack on Hash-based Image Retrieval via Clean-label Data Poisoning](https://mlsanity.com/paper/2109.08868/) (2021)
- [SEMICON: A Learning-to-hash Solution for Large-scale Fine-grained Image Retrieval](https://mlsanity.com/paper/2209.13833/) (2022)
- [Distilling and Transferring Knowledge via cGAN-generated Samples for Image Classification and Regression](https://mlsanity.com/paper/2104.03164/) (2021)
- [Accelerating Code Search with Deep Hashing and Code Classification](https://mlsanity.com/paper/2203.15287/) (2022)
- [HashVFL: Defending Against Data Reconstruction Attacks in Vertical Federated Learning](https://mlsanity.com/paper/2212.00325/) (2022)
- [Vision Transformer Hashing for Image Retrieval](https://mlsanity.com/paper/2109.12564/) (2021)
- [Deep Hash Distillation for Image Retrieval](https://mlsanity.com/paper/2112.08816/) (2021)
- [One Loss for Quantization: Deep Hashing with Discrete Wasserstein Distributional Matching](https://mlsanity.com/paper/2205.15721/) (2022)
- [Hyperbolic Hierarchical Contrastive Hashing](https://mlsanity.com/paper/2212.08904/) (2022)
- [TransHash: Transformer-based Hamming Hashing for Efficient Image Retrieval](https://mlsanity.com/paper/2105.01823/) (2021)
- [Prototype-supervised Adversarial Network for Targeted Attack of Deep Hashing](https://mlsanity.com/paper/2105.07553/) (2021)
- [Hybrid Contrastive Quantization for Efficient Cross-View Video Retrieval](https://mlsanity.com/paper/2202.03384/) (2022)
- [Attribute-Aware Deep Hashing with Self-Consistency for Large-Scale Fine-Grained Image Retrieval](https://mlsanity.com/paper/2311.12894/) (2023)
- [LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary Codes](https://mlsanity.com/paper/2106.01487/) (2021)

## Abstract (arXiv)

Learning to hash has been widely applied to approximate nearest neighbor search for large-scale multimedia retrieval, due to its computation efficiency and retrieval quality. Deep learning to hash, which improves retrieval quality by end-to-end representation learning and hash encoding, has received increasing attention recently. Subject to the ill-posed gradient difficulty in the optimization with sign activations, existing deep learning to hash methods need to first learn continuous representations and then generate binary hash codes in a separated binarization step, which suffer from substantial loss of retrieval quality. This work presents HashNet, a novel deep architecture for deep learning to hash by continuation method with convergence guarantees, which learns exactly binary hash codes from imbalanced similarity data. The key idea is to attack the ill-posed gradient problem in optimizing deep networks with non-smooth binary activations by continuation method, in which we begin from learning an easier network with smoothed activation function and let it evolve during the training, until it eventually goes back to being the original, difficult to optimize, deep network with the sign activation function. Comprehensive empirical evidence shows that HashNet can generate exactly binary hash codes and yield state-of-the-art multimedia retrieval performance on standard benchmarks.