On the Exploration of Incremental Learning for Fine-grained Image Retrieval
This addresses the incremental learning challenge for fine-grained image retrieval, which is incremental as it builds on existing methods to handle new classes without retraining.
The paper tackles the problem of catastrophic forgetting in incremental fine-grained image retrieval when new categories are added, proposing a method that uses soft labels and Maximum Mean Discrepancy regularization to mitigate performance degradation, achieving effective results on two datasets.
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.