# Asymmetric Transfer Hashing with Adaptive Bipartite Graph Learning

arXiv: https://arxiv.org/abs/2206.12592 · HTML: https://mlsanity.com/paper/2206.12592/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 70 references that are in the map.
- First posted on arXiv 25 Jun 2022.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition](https://mlsanity.com/paper/1310.1531/) (2013)
- [A Survey on Learning to Hash](https://mlsanity.com/paper/1606.00185/) (2016)
- [Efficient Diffusion on Region Manifolds: Recovering Small Objects with Compact CNN Representations](https://mlsanity.com/paper/1611.05113/) (2016)
- [Supervised Discrete Hashing](https://mlsanity.com/paper/1503.01557/) (2015)
- [Asymmetric Deep Supervised Hashing](https://mlsanity.com/paper/1707.08325/) (2017)
- [Adversarial Bipartite Graph Learning for Video Domain Adaptation](https://mlsanity.com/paper/2007.15829/) (2020)
- [Syn2Real: A New Benchmark forSynthetic-to-Real Visual Domain Adaptation](https://mlsanity.com/paper/1806.09755/) (2018)
- [Fast Supervised Discrete Hashing](https://mlsanity.com/paper/1904.03556/) (2019)
- [Probability Weighted Compact Feature for Domain Adaptive Retrieval](https://mlsanity.com/paper/2003.03293/) (2020)
- [Optimal Projection Guided Transfer Hashing for Image Retrieval](https://mlsanity.com/paper/1903.00252/) (2019)
- [Collaborative Learning for Extremely Low Bit Asymmetric Hashing](https://mlsanity.com/paper/1809.09329/) (2018)
- [SADIH: Semantic-Aware DIscrete Hashing](https://mlsanity.com/paper/1904.01739/) (2019)
- [The Power of Asymmetry in Binary Hashing](https://mlsanity.com/paper/1311.7662/) (2013)
- [Real-time Human Action Recognition Using Locally Aggregated Kinematic-Guided Skeletonlet and Supervised Hashing-by-Analysis Model](https://mlsanity.com/paper/2105.11312/) (2021)
- [Deep Asymmetric Hashing with Dual Semantic Regression and Class Structure Quantization](https://mlsanity.com/paper/2110.12478/) (2021)
- [Transfer Adversarial Hashing for Hamming Space Retrieval](https://mlsanity.com/paper/1712.04616/) (2017)

## Abstract (arXiv)

Thanks to the efficient retrieval speed and low storage consumption, learning to hash has been widely used in visual retrieval tasks. However, existing hashing methods assume that the query and retrieval samples lie in homogeneous feature space within the same domain. As a result, they cannot be directly applied to heterogeneous cross-domain retrieval. In this paper, we propose a Generalized Image Transfer Retrieval (GITR) problem, which encounters two crucial bottlenecks: 1) the query and retrieval samples may come from different domains, leading to an inevitable {domain distribution gap}; 2) the features of the two domains may be heterogeneous or misaligned, bringing up an additional {feature gap}. To address the GITR problem, we propose an Asymmetric Transfer Hashing (ATH) framework with its unsupervised/semi-supervised/supervised realizations. Specifically, ATH characterizes the domain distribution gap by the discrepancy between two asymmetric hash functions, and minimizes the feature gap with the help of a novel adaptive bipartite graph constructed on cross-domain data. By jointly optimizing asymmetric hash functions and the bipartite graph, not only can knowledge transfer be achieved but information loss caused by feature alignment can also be avoided. Meanwhile, to alleviate negative transfer, the intrinsic geometrical structure of single-domain data is preserved by involving a domain affinity graph. Extensive experiments on both single-domain and cross-domain benchmarks under different GITR subtasks indicate the superiority of our ATH method in comparison with the state-of-the-art hashing methods.