# Hot-Refresh Model Upgrades with Regression-Alleviating Compatible Training in Image Retrieval

arXiv: https://arxiv.org/abs/2201.09724 · HTML: https://mlsanity.com/paper/2201.09724/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 41 references that are in the map.
- First posted on arXiv 24 Jan 2022.

## Builds on (most cited first, 26 of 26)

- [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)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrieval](https://mlsanity.com/paper/2004.01804/) (2020)
- [Omni-Scale Feature Learning for Person Re-Identification](https://mlsanity.com/paper/1905.00953/) (2019)
- [Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification](https://mlsanity.com/paper/2001.01526/) (2020)
- [Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID](https://mlsanity.com/paper/2006.02713/) (2020)
- [Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking](https://mlsanity.com/paper/1803.11285/) (2018)
- [Deep Learning Face Representation by Joint Identification-Verification](https://mlsanity.com/paper/1406.4773/) (2014)
- [Deep Image Retrieval: Learning global representations for image search](https://mlsanity.com/paper/1604.01325/) (2016)
- [Self-supervising Fine-grained Region Similarities for Large-scale Image Localization](https://mlsanity.com/paper/2006.03926/) (2020)
- [Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrieval](https://mlsanity.com/paper/2007.12163/) (2020)
- [Blockwisely Supervised Neural Architecture Search with Knowledge Distillation](https://mlsanity.com/paper/1911.13053/) (2019)
- [Towards Backward-Compatible Representation Learning](https://mlsanity.com/paper/2003.11942/) (2020)
- [Positive-Congruent Training: Towards Regression-Free Model Updates](https://mlsanity.com/paper/2011.09161/) (2020)
- [DarkRank: Accelerating Deep Metric Learning via Cross Sample Similarities Transfer](https://mlsanity.com/paper/1707.01220/) (2017)
- [An Empirical Analysis of Backward Compatibility in Machine Learning Systems](https://mlsanity.com/paper/2008.04572/) (2020)
- [Learning Compatible Embeddings](https://mlsanity.com/paper/2108.01958/) (2021)
- [Unified Representation Learning for Cross Model Compatibility](https://mlsanity.com/paper/2008.04821/) (2020)
- [Asymmetric metric learning for knowledge transfer](https://mlsanity.com/paper/2006.16331/) (2020)
- [Compatibility-aware Heterogeneous Visual Search](https://mlsanity.com/paper/2105.06047/) (2021)
- [Continual Learning for Image-Based Camera Localization](https://mlsanity.com/paper/2108.09112/) (2021)
- [Regression Bugs Are In Your Model! Measuring, Reducing and Analyzing Regressions In NLP Model Updates](https://mlsanity.com/paper/2105.03048/) (2021)
- [1st Place Solution to Google Landmark Retrieval 2020](https://mlsanity.com/paper/2009.05132/) (2020)
- [Feature Lenses: Plug-and-play Neural Modules for Transformation-Invariant Visual Representations](https://mlsanity.com/paper/2004.05554/) (2020)

## Built on by (most cited first, 7 of 7)

- [Privacy-Preserving Model Upgrades with Bidirectional Compatible Training in Image Retrieval](https://mlsanity.com/paper/2204.13919/) (2022)
- [BT2: Backward-compatible Training with Basis Transformation](https://mlsanity.com/paper/2211.03989/) (2022)
- [Binary Embedding-based Retrieval at Tencent](https://mlsanity.com/paper/2302.08714/) (2023)
- [Darwinian Model Upgrades: Model Evolving with Selective Compatibility](https://mlsanity.com/paper/2210.06954/) (2022)
- [Towards Cross-modal Backward-compatible Representation Learning for Vision-Language Models](https://mlsanity.com/paper/2405.14715/) (2024)
- [Learning Along the Arrow of Time: Hyperbolic Geometry for Backward-Compatible Representation Learning](https://mlsanity.com/paper/2506.05826/) (2025)
- [Structure Similarity Preservation Learning for Asymmetric Image Retrieval](https://mlsanity.com/paper/2403.00648/) (2024)

## Abstract (arXiv)

The task of hot-refresh model upgrades of image retrieval systems plays an essential role in the industry but has never been investigated in academia before. Conventional cold-refresh model upgrades can only deploy new models after the gallery is overall backfilled, taking weeks or even months for massive data. In contrast, hot-refresh model upgrades deploy the new model immediately and then gradually improve the retrieval accuracy by backfilling the gallery on-the-fly. Compatible training has made it possible, however, the problem of model regression with negative flips poses a great challenge to the stable improvement of user experience. We argue that it is mainly due to the fact that new-to-old positive query-gallery pairs may show less similarity than new-to-new negative pairs. To solve the problem, we introduce a Regression-Alleviating Compatible Training (RACT) method to properly constrain the feature compatibility while reducing negative flips. The core is to encourage the new-to-old positive pairs to be more similar than both the new-to-old negative pairs and the new-to-new negative pairs. An efficient uncertainty-based backfilling strategy is further introduced to fasten accuracy improvements. Extensive experiments on large-scale retrieval benchmarks (e.g., Google Landmark) demonstrate that our RACT effectively alleviates the model regression for one more step towards seamless model upgrades. The code will be available at https://github.com/binjiezhang/RACT_ICLR2022.