# Dual-Tuning: Joint Prototype Transfer and Structure Regularization for Compatible Feature Learning

arXiv: https://arxiv.org/abs/2108.02959 · HTML: https://mlsanity.com/paper/2108.02959/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 62 references that are in the map.
- First posted on arXiv 6 Aug 2021.

## Builds on (most cited first, 30 of 37)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning](https://mlsanity.com/paper/1711.05769/) (2017)
- [Person Transfer GAN to Bridge Domain Gap for Person Re-Identification](https://mlsanity.com/paper/1711.08565/) (2017)
- [Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)](https://mlsanity.com/paper/1711.09349/) (2017)
- [ResNeSt: Split-Attention Networks](https://mlsanity.com/paper/2004.08955/) (2020)
- [Circle Loss: A Unified Perspective of Pair Similarity Optimization](https://mlsanity.com/paper/2002.10857/) (2020)
- [Omni-Scale Feature Learning for Person Re-Identification](https://mlsanity.com/paper/1905.00953/) (2019)
- [Multi-Adversarial Domain Adaptation](https://mlsanity.com/paper/1809.02176/) (2018)
- [SoftTriple Loss: Deep Metric Learning Without Triplet Sampling](https://mlsanity.com/paper/1909.05235/) (2019)
- [A Strong Baseline and Batch Normalization Neck for Deep Person Re-identification](https://mlsanity.com/paper/1906.08332/) (2019)
- [Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1705.00609/) (2017)
- [Deep Image Retrieval: Learning global representations for image search](https://mlsanity.com/paper/1604.01325/) (2016)
- [Cross-domain Detection via Graph-induced Prototype Alignment](https://mlsanity.com/paper/2003.12849/) (2020)
- [Human Semantic Parsing for Person Re-identification](https://mlsanity.com/paper/1804.00216/) (2018)
- [Towards Backward-Compatible Representation Learning](https://mlsanity.com/paper/2003.11942/) (2020)
- [The Devil of Face Recognition is in the Noise](https://mlsanity.com/paper/1807.11649/) (2018)
- [Learning Metrics from Teachers: Compact Networks for Image Embedding](https://mlsanity.com/paper/1904.03624/) (2019)
- [Knowledge Transfer via Dense Cross-Layer Mutual-Distillation](https://mlsanity.com/paper/2008.07816/) (2020)
- [Beyond Triplet Loss: Person Re-identification with Fine-grained Difference-aware Pairwise Loss](https://mlsanity.com/paper/2009.10295/) (2020)
- [PAMTRI: Pose-Aware Multi-Task Learning for Vehicle Re-Identification Using Highly Randomized Synthetic Data](https://mlsanity.com/paper/2005.00673/) (2020)

## Built on by (most cited first, 9 of 9)

- [Metric Compatible Training for Online Backfilling in Large-Scale Retrieval](https://mlsanity.com/paper/2301.03767/) (2023)
- [Large-to-small Image Resolution Asymmetry in Deep Metric Learning](https://mlsanity.com/paper/2210.05463/) (2022)
- [MixBCT: Towards Self-Adapting Backward-Compatible Training](https://mlsanity.com/paper/2308.06948/) (2023)
- [Structure Similarity Preservation Learning for Asymmetric Image Retrieval](https://mlsanity.com/paper/2403.00648/) (2024)
- [Prototype Perturbation for Relaxing Alignment Constraints in Backward-Compatible Learning](https://mlsanity.com/paper/2503.14824/) (2025)
- [Towards Test-time Efficient Visual Place Recognition via Asymmetric Query Processing](https://mlsanity.com/paper/2512.13055/) (2025)
- [Mining and Transferring Feature-Geometry Coherence for Unsupervised Point Cloud Registration](https://mlsanity.com/paper/2411.01870/) (2024)
- [A Stationary (and Therefore Compatible) Representation is All You Need](https://mlsanity.com/paper/2606.12488/) (2026)
- [Learning Compatible Multi-Prize Subnetworks for Asymmetric Retrieval](https://mlsanity.com/paper/2504.11879/) (2025)

## Abstract (arXiv)

Visual retrieval system faces frequent model update and deployment. It is a heavy workload to re-extract features of the whole database every time.Feature compatibility enables the learned new visual features to be directly compared with the old features stored in the database. In this way, when updating the deployed model, we can bypass the inflexible and time-consuming feature re-extraction process. However, the old feature space that needs to be compatible is not ideal and faces the distribution discrepancy problem with the new space caused by different supervision losses. In this work, we propose a global optimization Dual-Tuning method to obtain feature compatibility against different networks and losses. A feature-level prototype loss is proposed to explicitly align two types of embedding features, by transferring global prototype information. Furthermore, we design a component-level mutual structural regularization to implicitly optimize the feature intrinsic structure. Experimental results on million-scale datasets demonstrate that our Dual-Tuning is able to obtain feature compatibility without sacrificing performance. (Our code will be avaliable at https://github.com/yanbai1993/Dual-Tuning)