# Generative Negative Text Replay for Continual Vision-Language Pretraining

arXiv: https://arxiv.org/abs/2210.17322 · HTML: https://mlsanity.com/paper/2210.17322/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Placed in Prompt learning and adaptation of CLIP, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 36 of its 54 references that are in the map.
- First posted on arXiv 31 Oct 2022.

## Placed in

- Multimodal LLMs / vision-language models / [Prompt learning and adaptation of CLIP](https://mlsanity.com/mllm/prompt-learning-and-adaptation-of-clip/)

## Builds on (most cited first, 30 of 36)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [CNN-generated images are surprisingly easy to spot... for now](https://mlsanity.com/paper/1912.11035/) (2019)
- [Large Scale Incremental Learning](https://mlsanity.com/paper/1905.13260/) (2019)
- [Overcoming catastrophic forgetting with hard attention to the task](https://mlsanity.com/paper/1801.01423/) (2018)
- [Contrastive Learning with Hard Negative Samples](https://mlsanity.com/paper/2010.04592/) (2020)
- [End-to-End Incremental Learning](https://mlsanity.com/paper/1807.09536/) (2018)
- [Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion](https://mlsanity.com/paper/1912.08795/) (2019)
- [Unifying Vision-and-Language Tasks via Text Generation](https://mlsanity.com/paper/2102.02779/) (2021)
- [Online Continual Learning with Maximally Interfered Retrieval](https://mlsanity.com/paper/1908.04742/) (2019)
- [DER: Dynamically Expandable Representation for Class Incremental Learning](https://mlsanity.com/paper/2103.16788/) (2021)
- [Maintaining Discrimination and Fairness in Class Incremental Learning](https://mlsanity.com/paper/1911.07053/) (2019)
- [Co2L: Contrastive Continual Learning](https://mlsanity.com/paper/2106.14413/) (2021)
- [Continual Unsupervised Representation Learning](https://mlsanity.com/paper/1910.14481/) (2019)
- [Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learning](https://mlsanity.com/paper/2106.09701/) (2021)
- [Uncertainty-guided Continual Learning with Bayesian Neural Networks](https://mlsanity.com/paper/1906.02425/) (2019)
- [Contrastive Embedding for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2103.16173/) (2021)
- [On Learning the Geodesic Path for Incremental Learning](https://mlsanity.com/paper/2104.08572/) (2021)

## Built on by (most cited first, 18 of 18)

- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [Class-Incremental Learning: A Survey](https://mlsanity.com/paper/2302.03648/) (2023)
- [Lifelong Learning of Large Language Model based Agents: A Roadmap](https://mlsanity.com/paper/2501.07278/) (2025)
- [Recent Advances of Multimodal Continual Learning: A Comprehensive Survey](https://mlsanity.com/paper/2410.05352/) (2024)
- [Audio-Visual Class-Incremental Learning](https://mlsanity.com/paper/2308.11073/) (2023)
- [Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting](https://mlsanity.com/paper/2508.04227/) (2025)
- [Wakening Past Concepts without Past Data: Class-Incremental Learning from Online Placebos](https://mlsanity.com/paper/2310.16115/) (2023)
- [Continual Learning with Neuromorphic Computing: Foundations, Methods, and Emerging Applications](https://mlsanity.com/paper/2410.09218/) (2024)
- [Continual Audio-Visual Sound Separation](https://mlsanity.com/paper/2411.02860/) (2024)
- [Continual Retinal Vision-Language Pre-training upon Incremental Imaging Modalities](https://mlsanity.com/paper/2506.19320/) (2025)
- [GrowCLIP: Data-aware Automatic Model Growing for Large-scale Contrastive Language-Image Pre-training](https://mlsanity.com/paper/2308.11331/) (2023)
- [CovarNav: Machine Unlearning via Model Inversion and Covariance Navigation](https://mlsanity.com/paper/2311.12999/) (2023)
- [STELLA: Continual Audio-Video Pre-training with Spatio-Temporal Localized Alignment](https://mlsanity.com/paper/2310.08204/) (2023)
- [VLMs meet UDA: Boosting Transferability of Open Vocabulary Segmentation with Unsupervised Domain Adaptation](https://mlsanity.com/paper/2412.09240/) (2024)
- [DSCA: Dynamic Subspace Concept Alignment for Lifelong VLM Editing](https://mlsanity.com/paper/2604.07965/) (2026)
- [Attention-Spectrum Regularization for Replay-Free Continual Multimodal LLMs](https://mlsanity.com/paper/2606.23063/) (2026)
- [Lifelong Representations: A Survey on Continual Self-Supervised Learning for Vision Models](https://mlsanity.com/paper/2607.09785/) (2026)
- [AlphaWiSE: Adaptive Weight Interpolation for Continual Multimodal Representation Learning](https://mlsanity.com/paper/2607.15094/) (2026)

## Abstract (arXiv)

Vision-language pre-training (VLP) has attracted increasing attention recently. With a large amount of image-text pairs, VLP models trained with contrastive loss have achieved impressive performance in various tasks, especially the zero-shot generalization on downstream datasets. In practical applications, however, massive data are usually collected in a streaming fashion, requiring VLP models to continuously integrate novel knowledge from incoming data and retain learned knowledge. In this work, we focus on learning a VLP model with sequential chunks of image-text pair data. To tackle the catastrophic forgetting issue in this multi-modal continual learning setting, we first introduce pseudo text replay that generates hard negative texts conditioned on the training images in memory, which not only better preserves learned knowledge but also improves the diversity of negative samples in the contrastive loss. Moreover, we propose multi-modal knowledge distillation between images and texts to align the instance-wise prediction between old and new models. We incrementally pre-train our model on both the instance and class incremental splits of the Conceptual Caption dataset, and evaluate the model on zero-shot image classification and image-text retrieval tasks. Our method consistently outperforms the existing baselines with a large margin, which demonstrates its superiority. Notably, we realize an average performance boost of 4.60% on image-classification downstream datasets for the class incremental split.