# On the Exploration of Incremental Learning for Fine-grained Image Retrieval

arXiv: https://arxiv.org/abs/2010.08020 · HTML: https://mlsanity.com/paper/2010.08020/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Oct 2020.

## Built on by (most cited first, 12 of 12)

- [Deep Learning for Instance Retrieval: A Survey](https://mlsanity.com/paper/2101.11282/) (2021)
- [Lifelong Person Re-Identification via Adaptive Knowledge Accumulation](https://mlsanity.com/paper/2103.12462/) (2021)
- [Continual Learning for Visual Search with Backward Consistent Feature Embedding](https://mlsanity.com/paper/2205.13384/) (2022)
- [Fine-Grained Fashion Similarity Prediction by Attribute-Specific Embedding Learning](https://mlsanity.com/paper/2104.02429/) (2021)
- [AirLoop: Lifelong Loop Closure Detection](https://mlsanity.com/paper/2109.08975/) (2021)
- [CL2R: Compatible Lifelong Learning Representations](https://mlsanity.com/paper/2211.09032/) (2022)
- [Fine-Grained Adversarial Semi-supervised Learning](https://mlsanity.com/paper/2110.05848/) (2021)
- [Contrastive Supervised Distillation for Continual Representation Learning](https://mlsanity.com/paper/2205.05476/) (2022)
- [Positive Pair Distillation Considered Harmful: Continual Meta Metric Learning for Lifelong Object Re-Identification](https://mlsanity.com/paper/2210.01600/) (2022)
- [GaitAdapt: Continual Learning for Evolving Gait Recognition](https://mlsanity.com/paper/2508.03375/) (2025)
- [A Stationary (and Therefore Compatible) Representation is All You Need](https://mlsanity.com/paper/2606.12488/) (2026)
- [Online Deep Metric Learning via Mutual Distillation](https://mlsanity.com/paper/2203.05201/) (2022)

## Abstract (arXiv)

In this paper, we consider the problem of fine-grained image retrieval in an incremental setting, when new categories are added over time. On the one hand, repeatedly training the representation on the extended dataset is time-consuming. On the other hand, fine-tuning the learned representation only with the new classes leads to catastrophic forgetting. To this end, we propose an incremental learning method to mitigate retrieval performance degradation caused by the forgetting issue. Without accessing any samples of the original classes, the classifier of the original network provides soft "labels" to transfer knowledge to train the adaptive network, so as to preserve the previous capability for classification. More importantly, a regularization function based on Maximum Mean Discrepancy is devised to minimize the discrepancy of new classes features from the original network and the adaptive network, respectively. Extensive experiments on two datasets show that our method effectively mitigates the catastrophic forgetting on the original classes while achieving high performance on the new classes.