# Prompt Distribution Learning

arXiv: https://arxiv.org/abs/2205.03340 · HTML: https://mlsanity.com/paper/2205.03340/

## Key facts

- Cited by 235 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 29 of its 51 references that are in the map.
- First posted on arXiv 6 May 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, 29 of 29)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification](https://mlsanity.com/paper/1709.00029/) (2017)
- [How Can We Know What Language Models Know?](https://mlsanity.com/paper/1911.12543/) (2019)
- [Unified Language Model Pre-training for Natural Language Understanding and Generation](https://mlsanity.com/paper/1905.03197/) (2019)
- [It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners](https://mlsanity.com/paper/2009.07118/) (2020)
- [Contrastive Learning of Medical Visual Representations from Paired Images and Text](https://mlsanity.com/paper/2010.00747/) (2020)
- [Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?](https://mlsanity.com/paper/2003.11539/) (2020)
- [VirTex: Learning Visual Representations from Textual Annotations](https://mlsanity.com/paper/2006.06666/) (2020)
- [Factual Probing Is [MASK]: Learning vs. Learning to Recall](https://mlsanity.com/paper/2104.05240/) (2021)
- [PTR: Prompt Tuning with Rules for Text Classification](https://mlsanity.com/paper/2105.11259/) (2021)
- [Learning Visual Features from Large Weakly Supervised Data](https://mlsanity.com/paper/1511.02251/) (2015)
- [Learning Visual Representations with Caption Annotations](https://mlsanity.com/paper/2008.01392/) (2020)
- [Learning Visual N-Grams from Web Data](https://mlsanity.com/paper/1612.09161/) (2016)
- [Regularizing Deep Networks with Semantic Data Augmentation](https://mlsanity.com/paper/2007.10538/) (2020)
- [The Application of Two-level Attention Models in Deep Convolutional Neural Network for Fine-grained Image Classification](https://mlsanity.com/paper/1411.6447/) (2014)

## Built on by (most cited first, 30 of 235)

- [Vision-Language Models for Vision Tasks: A Survey](https://mlsanity.com/paper/2304.00685/) (2023)
- [MaPLe: Multi-modal Prompt Learning](https://mlsanity.com/paper/2210.03117/) (2022)
- [Prompt-aligned Gradient for Prompt Tuning](https://mlsanity.com/paper/2205.14865/) (2022)
- [Visual-Language Prompt Tuning with Knowledge-guided Context Optimization](https://mlsanity.com/paper/2303.13283/) (2023)
- [Self-regulating Prompts: Foundational Model Adaptation without Forgetting](https://mlsanity.com/paper/2307.06948/) (2023)
- [Unified Vision and Language Prompt Learning](https://mlsanity.com/paper/2210.07225/) (2022)
- [Neural Prompt Search](https://mlsanity.com/paper/2206.04673/) (2022)
- [DDCoT: Duty-Distinct Chain-of-Thought Prompting for Multimodal Reasoning in Language Models](https://mlsanity.com/paper/2310.16436/) (2023)
- [Task Residual for Tuning Vision-Language Models](https://mlsanity.com/paper/2211.10277/) (2022)
- [SuS-X: Training-Free Name-Only Transfer of Vision-Language Models](https://mlsanity.com/paper/2211.16198/) (2022)
- [Low-Rank Few-Shot Adaptation of Vision-Language Models](https://mlsanity.com/paper/2405.18541/) (2024)
- [DualCoOp: Fast Adaptation to Multi-Label Recognition with Limited Annotations](https://mlsanity.com/paper/2206.09541/) (2022)
- [Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large Language Models](https://mlsanity.com/paper/2305.15023/) (2023)
- [Waffling around for Performance: Visual Classification with Random Words and Broad Concepts](https://mlsanity.com/paper/2306.07282/) (2023)
- [CLIPood: Generalizing CLIP to Out-of-Distributions](https://mlsanity.com/paper/2302.00864/) (2023)
- [Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning with Multimodal Models](https://mlsanity.com/paper/2301.06267/) (2023)
- [Learning without Forgetting for Vision-Language Models](https://mlsanity.com/paper/2305.19270/) (2023)
- [Consistency-guided Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2306.01195/) (2023)
- [GraphAdapter: Tuning Vision-Language Models With Dual Knowledge Graph](https://mlsanity.com/paper/2309.13625/) (2023)
- [BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIP](https://mlsanity.com/paper/2311.16194/) (2023)
- [On the test-time zero-shot generalization of vision-language models: Do we really need prompt learning?](https://mlsanity.com/paper/2405.02266/) (2024)
- [PLOT: Prompt Learning with Optimal Transport for Vision-Language Models](https://mlsanity.com/paper/2210.01253/) (2022)
- [Perceive-IR: Learning to Perceive Degradation Better for All-in-One Image Restoration](https://mlsanity.com/paper/2408.15994/) (2024)
- [LASP: Text-to-Text Optimization for Language-Aware Soft Prompting of Vision & Language Models](https://mlsanity.com/paper/2210.01115/) (2022)
- [PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization](https://mlsanity.com/paper/2307.15199/) (2023)
- [Sentence-level Prompts Benefit Composed Image Retrieval](https://mlsanity.com/paper/2310.05473/) (2023)
- [Diversity-Aware Meta Visual Prompting](https://mlsanity.com/paper/2303.08138/) (2023)
- [I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classification](https://mlsanity.com/paper/2212.02291/) (2022)
- [A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation](https://mlsanity.com/paper/2402.04087/) (2024)
- [Dual Modality Prompt Tuning for Vision-Language Pre-Trained Model](https://mlsanity.com/paper/2208.08340/) (2022)

## Abstract (arXiv)

We present prompt distribution learning for effectively adapting a pre-trained vision-language model to address downstream recognition tasks. Our method not only learns low-bias prompts from a few samples but also captures the distribution of diverse prompts to handle the varying visual representations. In this way, we provide high-quality task-related content for facilitating recognition. This prompt distribution learning is realized by an efficient approach that learns the output embeddings of prompts instead of the input embeddings. Thus, we can employ a Gaussian distribution to model them effectively and derive a surrogate loss for efficient training. Extensive experiments on 12 datasets demonstrate that our method consistently and significantly outperforms existing methods. For example, with 1 sample per category, it relatively improves the average result by 9.1% compared to human-crafted prompts.