# Improving Zero-Shot Generalization for CLIP with Synthesized Prompts

arXiv: https://arxiv.org/abs/2307.07397 · HTML: https://mlsanity.com/paper/2307.07397/

## Key facts

- Cited by 51 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 38 of its 55 references that are in the map.
- First posted on arXiv 14 Jul 2023.

## 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 38)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification](https://mlsanity.com/paper/1709.00029/) (2017)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)
- [VL-BERT: Pre-training of Generic Visual-Linguistic Representations](https://mlsanity.com/paper/1908.08530/) (2019)
- [Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly](https://mlsanity.com/paper/1707.00600/) (2017)
- [Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification](https://mlsanity.com/paper/2207.09519/) (2022)
- [Feature Generating Networks for Zero-Shot Learning](https://mlsanity.com/paper/1712.00981/) (2017)
- [Prompt Distribution Learning](https://mlsanity.com/paper/2205.03340/) (2022)
- [f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning](https://mlsanity.com/paper/1903.10132/) (2019)
- [Attribute Prototype Network for Zero-Shot Learning](https://mlsanity.com/paper/2008.08290/) (2020)
- [VLP: A Survey on Vision-Language Pre-training](https://mlsanity.com/paper/2202.09061/) (2022)
- [Large-scale Multi-Modal Pre-trained Models: A Comprehensive Survey](https://mlsanity.com/paper/2302.10035/) (2023)
- [Counterfactual Zero-Shot and Open-Set Visual Recognition](https://mlsanity.com/paper/2103.00887/) (2021)

## Built on by (most cited first, 30 of 51)

- [LoRA-Pro: Are Low-Rank Adapters Properly Optimized?](https://mlsanity.com/paper/2407.18242/) (2024)
- [A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation](https://mlsanity.com/paper/2402.04087/) (2024)
- [CLIP in Medical Imaging: A Survey](https://mlsanity.com/paper/2312.07353/) (2023)
- [R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuning](https://mlsanity.com/paper/2504.11195/) (2025)
- [AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation](https://mlsanity.com/paper/2407.04603/) (2024)
- [Improving Zero-shot Generalization of Learned Prompts via Unsupervised Knowledge Distillation](https://mlsanity.com/paper/2407.03056/) (2024)
- [LoRA-IR: Taming Low-Rank Experts for Efficient All-in-One Image Restoration](https://mlsanity.com/paper/2410.15385/) (2024)
- [Post-pre-training for Modality Alignment in Vision-Language Foundation Models](https://mlsanity.com/paper/2504.12717/) (2025)
- [Overcoming the Pitfalls of Vision-Language Model Finetuning for OOD Generalization](https://mlsanity.com/paper/2401.15914/) (2024)
- [Progressive Semantic-Guided Vision Transformer for Zero-Shot Learning](https://mlsanity.com/paper/2404.07713/) (2024)
- [Visual-Augmented Dynamic Semantic Prototype for Generative Zero-Shot Learning](https://mlsanity.com/paper/2404.14808/) (2024)
- [Lipsum-FT: Robust Fine-Tuning of Zero-Shot Models Using Random Text Guidance](https://mlsanity.com/paper/2404.00860/) (2024)
- [DeCoOp: Robust Prompt Tuning with Out-of-Distribution Detection](https://mlsanity.com/paper/2406.00345/) (2024)
- [Beyond Sole Strength: Customized Ensembles for Generalized Vision-Language Models](https://mlsanity.com/paper/2311.17091/) (2023)
- [Learning Prompt with Distribution-Based Feature Replay for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2401.01598/) (2024)
- [SAFT: Towards Out-of-Distribution Generalization in Fine-Tuning](https://mlsanity.com/paper/2407.03036/) (2024)
- [Unseen No More: Unlocking the Potential of CLIP for Generative Zero-shot HOI Detection](https://mlsanity.com/paper/2408.05974/) (2024)
- [Logits DeConfusion with CLIP for Few-Shot Learning](https://mlsanity.com/paper/2504.12104/) (2025)
- [ZeroDiff: Solidified Visual-Semantic Correlation in Zero-Shot Learning](https://mlsanity.com/paper/2406.02929/) (2024)
- [Efficient Test-Time Prompt Tuning for Vision-Language Models](https://mlsanity.com/paper/2408.05775/) (2024)
- [Data-Free Generalized Zero-Shot Learning](https://mlsanity.com/paper/2401.15657/) (2024)
- [Multi-Modal Adapter for Vision-Language Models](https://mlsanity.com/paper/2409.02958/) (2024)
- [Generalizing vision-language models to novel domains: A comprehensive survey](https://mlsanity.com/paper/2506.18504/) (2025)
- [CRoFT: Robust Fine-Tuning with Concurrent Optimization for OOD Generalization and Open-Set OOD Detection](https://mlsanity.com/paper/2405.16417/) (2024)
- [GenZSL: Generative Zero-Shot Learning Via Inductive Variational Autoencoder](https://mlsanity.com/paper/2505.11882/) (2025)
- [Aggregate-and-Adapt Natural Language Prompts for Downstream Generalization of CLIP](https://mlsanity.com/paper/2410.23698/) (2024)
- [Captured by Captions: On Memorization and its Mitigation in CLIP Models](https://mlsanity.com/paper/2502.07830/) (2025)
- [Efficient and Long-Tailed Generalization for Pre-trained Vision-Language Model](https://mlsanity.com/paper/2406.12638/) (2024)
- [Multi-Task Domain Adaptation for Language Grounding with 3D Objects](https://mlsanity.com/paper/2407.02846/) (2024)
- [ZeroMamba: Exploring Visual State Space Model for Zero-Shot Learning](https://mlsanity.com/paper/2408.14868/) (2024)

## Abstract (arXiv)

With the growing interest in pretrained vision-language models like CLIP, recent research has focused on adapting these models to downstream tasks. Despite achieving promising results, most existing methods require labeled data for all classes, which may not hold in real-world applications due to the long tail and Zipf's law. For example, some classes may lack labeled data entirely, such as emerging concepts. To address this problem, we propose a plug-and-play generative approach called SyntHesIzed Prompts~(SHIP) to improve existing fine-tuning methods. Specifically, we follow variational autoencoders to introduce a generator that reconstructs the visual features by inputting the synthesized prompts and the corresponding class names to the textual encoder of CLIP. In this manner, we easily obtain the synthesized features for the remaining label-only classes. Thereafter, we fine-tune CLIP with off-the-shelf methods by combining labeled and synthesized features. Extensive experiments on base-to-new generalization, cross-dataset transfer learning, and generalized zero-shot learning demonstrate the superiority of our approach. The code is available at urlhttps://github.com/mrflogs/SHIP.