# Incremental Embedding Learning via Zero-Shot Translation

arXiv: https://arxiv.org/abs/2012.15497 · HTML: https://mlsanity.com/paper/2012.15497/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Dec 2020.

## Built on by (most cited first, 11 of 11)

- [Class-Incremental Learning: A Survey](https://mlsanity.com/paper/2302.03648/) (2023)
- [DENSE: Data-Free One-Shot Federated Learning](https://mlsanity.com/paper/2112.12371/) (2021)
- [Continual Learning and Catastrophic Forgetting](https://mlsanity.com/paper/2403.05175/) (2024)
- [Image-free Classifier Injection for Zero-Shot Classification](https://mlsanity.com/paper/2308.10599/) (2023)
- [Domain-Smoothing Network for Zero-Shot Sketch-Based Image Retrieval](https://mlsanity.com/paper/2106.11841/) (2021)
- [InOR-Net: Incremental 3D Object Recognition Network for Point Cloud Representation](https://mlsanity.com/paper/2302.09886/) (2023)
- [Rebalanced Zero-shot Learning](https://mlsanity.com/paper/2210.07031/) (2022)
- [Incremental user embedding modeling for personalized text classification](https://mlsanity.com/paper/2202.06369/) (2022)
- [A novel spatial-frequency domain network for zero-shot incremental learning](https://mlsanity.com/paper/2402.07216/) (2024)
- [Class-Incremental Learning for Honey Botanical Origin Classification with Hyperspectral Images: A Study with Continual Backpropagation](https://mlsanity.com/paper/2506.10489/) (2025)
- [DIMoE-Adapters: Dynamic Expert Evolution for Continual Learning in Vision-Language Models](https://mlsanity.com/paper/2605.07494/) (2026)

## Abstract (arXiv)

Modern deep learning methods have achieved great success in machine learning and computer vision fields by learning a set of pre-defined datasets. Howerver, these methods perform unsatisfactorily when applied into real-world situations. The reason of this phenomenon is that learning new tasks leads the trained model quickly forget the knowledge of old tasks, which is referred to as catastrophic forgetting. Current state-of-the-art incremental learning methods tackle catastrophic forgetting problem in traditional classification networks and ignore the problem existing in embedding networks, which are the basic networks for image retrieval, face recognition, zero-shot learning, etc. Different from traditional incremental classification networks, the semantic gap between the embedding spaces of two adjacent tasks is the main challenge for embedding networks under incremental learning setting. Thus, we propose a novel class-incremental method for embedding network, named as zero-shot translation class-incremental method (ZSTCI), which leverages zero-shot translation to estimate and compensate the semantic gap without any exemplars. Then, we try to learn a unified representation for two adjacent tasks in sequential learning process, which captures the relationships of previous classes and current classes precisely. In addition, ZSTCI can easily be combined with existing regularization-based incremental learning methods to further improve performance of embedding networks. We conduct extensive experiments on CUB-200-2011 and CIFAR100, and the experiment results prove the effectiveness of our method. The code of our method has been released.