# Cross-Modal Prototype Alignment and Mixing for Training-Free Few-Shot Classification

arXiv: https://arxiv.org/abs/2603.24528 · HTML: https://mlsanity.com/paper/2603.24528/

## Key facts

- Cited by 2 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 28 of its 43 references that are in the map.
- First posted on arXiv 25 Mar 2026.

## 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, 28 of 28)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [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)
- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)
- [MaPLe: Multi-modal Prompt Learning](https://mlsanity.com/paper/2210.03117/) (2022)
- [Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning](https://mlsanity.com/paper/2203.02053/) (2022)
- [Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification](https://mlsanity.com/paper/2207.09519/) (2022)
- [Perception Encoder: The best visual embeddings are not at the output of the network](https://mlsanity.com/paper/2504.13181/) (2025)
- [Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP](https://mlsanity.com/paper/2308.02487/) (2023)
- [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)
- [Why are Visually-Grounded Language Models Bad at Image Classification?](https://mlsanity.com/paper/2405.18415/) (2024)
- [Not All Features Matter: Enhancing Few-shot CLIP with Adaptive Prior Refinement](https://mlsanity.com/paper/2304.01195/) (2023)
- [CLIP for All Things Zero-Shot Sketch-Based Image Retrieval, Fine-Grained or Not](https://mlsanity.com/paper/2303.13440/) (2023)
- [A Closer Look at the Few-Shot Adaptation of Large Vision-Language Models](https://mlsanity.com/paper/2312.12730/) (2023)
- [Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models](https://mlsanity.com/paper/2404.07983/) (2024)
- [A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation](https://mlsanity.com/paper/2402.04087/) (2024)
- [Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion](https://mlsanity.com/paper/2502.04263/) (2025)
- [The Double-Ellipsoid Geometry of CLIP](https://mlsanity.com/paper/2411.14517/) (2024)
- [Text-Guided Attention is All You Need for Zero-Shot Robustness in Vision-Language Models](https://mlsanity.com/paper/2410.21802/) (2024)
- [ProKeR: A Kernel Perspective on Few-Shot Adaptation of Large Vision-Language Models](https://mlsanity.com/paper/2501.11175/) (2025)
- [SpectralGCD: Spectral Concept Selection and Cross-modal Representation Learning for Generalized Category Discovery](https://mlsanity.com/paper/2602.17395/) (2026)
- [Generative Giants, Retrieval Weaklings: Why do Multimodal Large Language Models Fail at Multimodal Retrieval?](https://mlsanity.com/paper/2512.19115/) (2025)

## Built on by (most cited first, 2 of 2)

- [Scalable Semantic Steering of Embedding Projections](https://mlsanity.com/paper/2607.03978/) (2026)
- [The Blending Ratio Is Not Where the Performance Is: Diagnosing Prototype Blending for Few-Shot Adaptation of Vision-Language Models](https://mlsanity.com/paper/2608.23634/) (2026)

## Abstract (arXiv)

Vision-language models like CLIP are trained with the objective of aligning text and image pairs. Beyond text prompts alone, recent works show that exploiting few-shot image embeddings from a training set is effective for CLIP-based classification. In this work, we analyze mixing image and text prototypes from a bias-variance perspective and show that mixing prototypes acts like a variance shrinkage estimator. Naively mixing text and image prototypes combines two partially aligned spaces since the two modalities are not perfectly aligned. To address this, we project image prototypes onto the principal directions of the semantic text embedding space to obtain a task-semantic image subspace. Mixing the image prototypes with text embeddings in the task-semantic subspace improves few-shot classification. However, when the task-semantic subspace captures insufficient discriminative visual information, relying on this subspace alone can be suboptimal. On extensive experiments over several few-shot classification benchmarks, we show that combining a task-semantic mixed prototype classifier and an anisotropic image-specific classifier systematically outperforms existing methods.