# Enhancing Zero-Shot Vision Models by Label-Free Prompt Distribution Learning and Bias Correcting

arXiv: https://arxiv.org/abs/2410.19294 · HTML: https://mlsanity.com/paper/2410.19294/

## Key facts

- Cited by 26 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 39 of its 51 references that are in the map.
- First posted on arXiv 25 Oct 2024.

## 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 39)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [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)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [Do ImageNet Classifiers Generalize to ImageNet?](https://mlsanity.com/paper/1902.10811/) (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)
- [Natural Adversarial Examples](https://mlsanity.com/paper/1907.07174/) (2019)
- [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022)
- [Learning Robust Global Representations by Penalizing Local Predictive Power](https://mlsanity.com/paper/1905.13549/) (2019)
- [Robust fine-tuning of zero-shot models](https://mlsanity.com/paper/2109.01903/) (2021)
- [Long-tail learning via logit adjustment](https://mlsanity.com/paper/2007.07314/) (2020)
- [Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models](https://mlsanity.com/paper/2209.07511/) (2022)
- [Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification](https://mlsanity.com/paper/2207.09519/) (2022)
- [Prompt-aligned Gradient for Prompt Tuning](https://mlsanity.com/paper/2205.14865/) (2022)
- [What does a platypus look like? Generating customized prompts for zero-shot image classification](https://mlsanity.com/paper/2209.03320/) (2022)
- [Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect](https://mlsanity.com/paper/2009.12991/) (2020)
- [Prompt Distribution Learning](https://mlsanity.com/paper/2205.03340/) (2022)
- [Disentangling Label Distribution for Long-tailed Visual Recognition](https://mlsanity.com/paper/2012.00321/) (2020)
- [Efficient Test-Time Adaptation of Vision-Language Models](https://mlsanity.com/paper/2403.18293/) (2024)
- [SuS-X: Training-Free Name-Only Transfer of Vision-Language Models](https://mlsanity.com/paper/2211.16198/) (2022)
- [Align Your Prompts: Test-Time Prompting with Distribution Alignment for Zero-Shot Generalization](https://mlsanity.com/paper/2311.01459/) (2023)
- [Debiased Learning from Naturally Imbalanced Pseudo-Labels](https://mlsanity.com/paper/2201.01490/) (2022)
- [The Neglected Tails in Vision-Language Models](https://mlsanity.com/paper/2401.12425/) (2024)
- [A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation](https://mlsanity.com/paper/2402.04087/) (2024)
- [A Simple Zero-shot Prompt Weighting Technique to Improve Prompt Ensembling in Text-Image Models](https://mlsanity.com/paper/2302.06235/) (2023)
- [Black Box Few-Shot Adaptation for Vision-Language models](https://mlsanity.com/paper/2304.01752/) (2023)
- [GPT4Vis: What Can GPT-4 Do for Zero-shot Visual Recognition?](https://mlsanity.com/paper/2311.15732/) (2023)

## Built on by (most cited first, 26 of 26)

- [On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification](https://mlsanity.com/paper/2508.05629/) (2025)
- [Enhancing CLIP Robustness via Cross-Modality Alignment](https://mlsanity.com/paper/2510.24038/) (2025)
- [Accelerating Diffusion Transformer via Error-Optimized Cache](https://mlsanity.com/paper/2501.19243/) (2025)
- [Dynamic Multimodal Prototype Learning in Vision-Language Models](https://mlsanity.com/paper/2507.03657/) (2025)
- [Real-Time Motion-Controllable Autoregressive Video Diffusion](https://mlsanity.com/paper/2510.08131/) (2025)
- [CatRAG: Functor-Guided Structural Debiasing with Retrieval Augmentation for Fair LLMs](https://mlsanity.com/paper/2603.21524/) (2026)
- [Look Carefully: Adaptive Visual Reinforcements in Multimodal Large Language Models for Hallucination Mitigation](https://mlsanity.com/paper/2602.24041/) (2026)
- [ACE: Concept Editing in Diffusion Models without Performance Degradation](https://mlsanity.com/paper/2503.08116/) (2025)
- [Backpropagation-Free Test-Time Adaptation via Probabilistic Gaussian Alignment](https://mlsanity.com/paper/2508.15568/) (2025)
- [Hierarchical Semantic Alignment for Image Clustering](https://mlsanity.com/paper/2512.00904/) (2025)
- [Context-Aware Multimodal Pretraining](https://mlsanity.com/paper/2411.15099/) (2024)
- [ASAP: Unsupervised Post-training with Label Distribution Shift Adaptive Learning Rate](https://mlsanity.com/paper/2508.13445/) (2025)
- [Visual Diversity and Region-aware Prompt Learning for Zero-shot HOI Detection](https://mlsanity.com/paper/2510.25094/) (2025)
- [Adaptive Debiasing Tsallis Entropy for Test-Time Adaptation](https://mlsanity.com/paper/2602.11743/) (2026)
- [OASIS: Open-world Adaptive Self-supervised and Imbalanced-aware System](https://mlsanity.com/paper/2508.16656/) (2025)
- [Causality-guided Prompt Learning for Vision-language Models via Visual Granulation](https://mlsanity.com/paper/2509.03803/) (2025)
- [Principled Steering via Null-space Projection for Jailbreak Defense in Vision-Language Models](https://mlsanity.com/paper/2603.22094/) (2026)
- [Dual Distribution Estimation for Zero-shot Noisy Test-Time Adaptation with VLMs](https://mlsanity.com/paper/2606.25758/) (2026)
- [TOFA: Training-Free One-Shot Federated Adaptation for Vision-Language Models](https://mlsanity.com/paper/2511.16423/) (2025)
- [Adapting Point Cloud Analysis via Multimodal Bayesian Distribution Learning](https://mlsanity.com/paper/2603.22070/) (2026)
- [[CLS] is Not Enough: Multi-Label Recognition via Patch-Level Inference and Adaptive Aggregation](https://mlsanity.com/paper/2605.25821/) (2026)
- [The Geometry of Saturation: Effective Rank Predicts When Labels Stop Helping in Few-Shot Classification](https://mlsanity.com/paper/2606.24903/) (2026)
- [Dynamic Distribution-Aware Uncertainty Tracking in Vision-Language Representation Learning](https://mlsanity.com/paper/2608.09011/) (2026)
- [PEA-DPO: Perception-Enhanced Alignment Direct Preference Optimization for MLLMs Alignment](https://mlsanity.com/paper/2608.19598/) (2026)
- [Membership Inference in Fine-tuned Diffusion Language Models via Token-level Memorization Asymmetry](https://mlsanity.com/paper/2609.00873/) (2026)
- [Domain Recentering and Confidence-Weighted Prior Calibration for Vision-Language Models](https://mlsanity.com/paper/2609.29358/) (2026)

## Abstract (arXiv)

Vision-language models, such as CLIP, have shown impressive generalization capacities when using appropriate text descriptions. While optimizing prompts on downstream labeled data has proven effective in improving performance, these methods entail labor costs for annotations and are limited by their quality. Additionally, since CLIP is pre-trained on highly imbalanced Web-scale data, it suffers from inherent label bias that leads to suboptimal performance. To tackle the above challenges, we propose a label-Free prompt distribution learning and bias correction framework, dubbed as **Frolic**, which boosts zero-shot performance without the need for labeled data. Specifically, our Frolic learns distributions over prompt prototypes to capture diverse visual representations and adaptively fuses these with the original CLIP through confidence matching. This fused model is further enhanced by correcting label bias via a label-free logit adjustment. Notably, our method is not only training-free but also circumvents the necessity for hyper-parameter tuning. Extensive experimental results across 16 datasets demonstrate the efficacy of our approach, particularly outperforming the state-of-the-art by an average of 2.6% on 10 datasets with CLIP ViT-B/16 and achieving an average margin of 1.5% on ImageNet and its five distribution shifts with CLIP ViT-B/16. Codes are available in https://github.com/zhuhsingyuu/Frolic.