# Unseen Classes at a Later Time? No Problem

arXiv: https://arxiv.org/abs/2203.16517 · HTML: https://mlsanity.com/paper/2203.16517/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 35 references that are in the map.
- First posted on arXiv 30 Mar 2022.

## Builds on (most cited first, 20 of 20)

- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning](https://mlsanity.com/paper/1711.05769/) (2017)
- [Large-Scale Long-Tailed Recognition in an Open World](https://mlsanity.com/paper/1904.05160/) (2019)
- [Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly](https://mlsanity.com/paper/1707.00600/) (2017)
- [Deep Long-Tailed Learning: A Survey](https://mlsanity.com/paper/2110.04596/) (2021)
- [Feature Generating Networks for Zero-Shot Learning](https://mlsanity.com/paper/1712.00981/) (2017)
- [Semantic Drift Compensation for Class-Incremental Learning](https://mlsanity.com/paper/2004.00440/) (2020)
- [Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders](https://mlsanity.com/paper/1812.01784/) (2018)
- [Learning a Deep Embedding Model for Zero-Shot Learning](https://mlsanity.com/paper/1611.05088/) (2016)
- [Generative Feature Replay For Class-Incremental Learning](https://mlsanity.com/paper/2004.09199/) (2020)
- [Leveraging the Invariant Side of Generative Zero-Shot Learning](https://mlsanity.com/paper/1904.04092/) (2019)
- [A Generative Model For Zero Shot Learning Using Conditional Variational Autoencoders](https://mlsanity.com/paper/1709.00663/) (2017)
- [Leveraging Seen and Unseen Semantic Relationships for Generative Zero-Shot Learning](https://mlsanity.com/paper/2007.09549/) (2020)
- [Adversarial Training of Variational Auto-encoders for Continual Zero-shot Learning(A-CZSL)](https://mlsanity.com/paper/2102.03778/) (2021)
- [Dynamic VAEs with Generative Replay for Continual Zero-shot Learning](https://mlsanity.com/paper/2104.12468/) (2021)
- [Bookworm continual learning: beyond zero-shot learning and continual learning](https://mlsanity.com/paper/2006.15176/) (2020)

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

- [Open-Set Biometrics: Beyond Good Closed-Set Models](https://mlsanity.com/paper/2407.16133/) (2024)
- [Zero-shot-Learning Cross-Modality Data Translation Through Mutual Information Guided Stochastic Diffusion](https://mlsanity.com/paper/2301.13743/) (2023)
- [Open-Vocabulary Federated Learning with Multimodal Prototyping](https://mlsanity.com/paper/2404.01232/) (2024)
- [LocalScore: Local Density-Aware Similarity Scoring for Biometrics](https://mlsanity.com/paper/2602.01012/) (2026)
- [Meta-Learned Attribute Self-Interaction Network for Continual and Generalized Zero-Shot Learning](https://mlsanity.com/paper/2312.01167/) (2023)
- [Continual Zero-Shot Learning through Semantically Guided Generative Random Walks](https://mlsanity.com/paper/2308.12366/) (2023)
- [Learning to better see the unseen: Broad-Deep Mixed Anti-Forgetting Framework for Incremental Zero-Shot Fault Diagnosis](https://mlsanity.com/paper/2403.13845/) (2024)

## Abstract (arXiv)

Recent progress towards learning from limited supervision has encouraged efforts towards designing models that can recognize novel classes at test time (generalized zero-shot learning or GZSL). GZSL approaches assume knowledge of all classes, with or without labeled data, beforehand. However, practical scenarios demand models that are adaptable and can handle dynamic addition of new seen and unseen classes on the fly (that is continual generalized zero-shot learning or CGZSL). One solution is to sequentially retrain and reuse conventional GZSL methods, however, such an approach suffers from catastrophic forgetting leading to suboptimal generalization performance. A few recent efforts towards tackling CGZSL have been limited by difference in settings, practicality, data splits and protocols followed-inhibiting fair comparison and a clear direction forward. Motivated from these observations, in this work, we firstly consolidate the different CGZSL setting variants and propose a new Online-CGZSL setting which is more practical and flexible. Secondly, we introduce a unified feature-generative framework for CGZSL that leverages bi-directional incremental alignment to dynamically adapt to addition of new classes, with or without labeled data, that arrive over time in any of these CGZSL settings. Our comprehensive experiments and analysis on five benchmark datasets and comparison with baselines show that our approach consistently outperforms existing methods, especially on the more practical Online setting.