# Towards Visual Feature Translation

arXiv: https://arxiv.org/abs/1812.00573 · HTML: https://mlsanity.com/paper/1812.00573/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Dec 2018.

## Built on by (most cited first, 8 of 8)

- [Deep Learning for Instance Retrieval: A Survey](https://mlsanity.com/paper/2101.11282/) (2021)
- [Compatibility-aware Heterogeneous Visual Search](https://mlsanity.com/paper/2105.06047/) (2021)
- [CoReS: Compatible Representations via Stationarity](https://mlsanity.com/paper/2111.07632/) (2021)
- [Dual-Tuning: Joint Prototype Transfer and Structure Regularization for Compatible Feature Learning](https://mlsanity.com/paper/2108.02959/) (2021)
- [CL2R: Compatible Lifelong Learning Representations](https://mlsanity.com/paper/2211.09032/) (2022)
- [Improving Prediction Backward-Compatiblility in NLP Model Upgrade with Gated Fusion](https://mlsanity.com/paper/2302.02080/) (2023)
- [Large-to-small Image Resolution Asymmetry in Deep Metric Learning](https://mlsanity.com/paper/2210.05463/) (2022)
- [AsymLoc: Towards Asymmetric Feature Matching for Efficient Visual Localization](https://mlsanity.com/paper/2604.09445/) (2026)

## Abstract (arXiv)

Most existing visual search systems are deployed based upon fixed kinds of visual features, which prohibits the feature reusing across different systems or when upgrading systems with a new type of feature. Such a setting is obviously inflexible and time/memory consuming, which is indeed mendable if visual features can be "translated" across systems. In this paper, we make the first attempt towards visual feature translation to break through the barrier of using features across different visual search systems. To this end, we propose a Hybrid Auto-Encoder (HAE) to translate visual features, which learns a mapping by minimizing the translation and reconstruction errors. Based upon HAE, an Undirected Affinity Measurement (UAM) is further designed to quantify the affinity among different types of visual features. Extensive experiments have been conducted on several public datasets with sixteen different types of widely-used features in visual search systems. Quantitative results show the encouraging possibilities of feature translation. For the first time, the affinity among widely-used features like SIFT and DELF is reported.