# Making Large Vision Language Models to be Good Few-shot Learners

arXiv: https://arxiv.org/abs/2408.11297 · HTML: https://mlsanity.com/paper/2408.11297/

## Key facts

- Cited by 7 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 37 of its 51 references that are in the map.
- First posted on arXiv 21 Aug 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 37)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [Kosmos-2: Grounding Multimodal Large Language Models to the World](https://mlsanity.com/paper/2306.14824/) (2023)
- [Meta-Learning in Neural Networks: A Survey](https://mlsanity.com/paper/2004.05439/) (2020)
- [Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic](https://mlsanity.com/paper/2306.15195/) (2023)
- [Meta-Learning with Latent Embedding Optimization](https://mlsanity.com/paper/1807.05960/) (2018)
- [Meta-Learning for Semi-Supervised Few-Shot Classification](https://mlsanity.com/paper/1803.00676/) (2018)
- [Meta-learning with differentiable closed-form solvers](https://mlsanity.com/paper/1805.08136/) (2018)
- [Learning Deep Representations of Fine-grained Visual Descriptions](https://mlsanity.com/paper/1605.05395/) (2016)
- [ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models](https://mlsanity.com/paper/2204.08790/) (2022)
- [Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference](https://mlsanity.com/paper/2204.07305/) (2022)
- [Few-Shot Classification with Feature Map Reconstruction Networks](https://mlsanity.com/paper/2012.01506/) (2020)
- [Adaptive Cross-Modal Few-Shot Learning](https://mlsanity.com/paper/1902.07104/) (2019)
- [Boosting Few-Shot Learning With Adaptive Margin Loss](https://mlsanity.com/paper/2005.13826/) (2020)
- [Prototype Completion with Primitive Knowledge for Few-Shot Learning](https://mlsanity.com/paper/2009.04960/) (2020)
- [Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classification](https://mlsanity.com/paper/2204.04567/) (2022)
- [Generating Representative Samples for Few-Shot Classification](https://mlsanity.com/paper/2205.02918/) (2022)
- [Semantic Prompt for Few-Shot Image Recognition](https://mlsanity.com/paper/2303.14123/) (2023)

## Built on by (most cited first, 7 of 7)

- [edgeVLM: Cloud-edge Collaborative Real-time VLM based on Context Transfer](https://mlsanity.com/paper/2508.12638/) (2025)
- [Verbalized Representation Learning for Interpretable Few-Shot Generalization](https://mlsanity.com/paper/2411.18651/) (2024)
- [MPCAR: Multi-Perspective Contextual Augmentation for Enhanced Visual Reasoning in Large Vision-Language Models](https://mlsanity.com/paper/2508.12400/) (2025)
- [MPA: Multimodal Prototype Augmentation for Few-Shot Learning](https://mlsanity.com/paper/2602.10143/) (2026)
- [Unlocking Few-Shot Capabilities in LVLMs via Prompt Conditioning and Head Selection](https://mlsanity.com/paper/2603.24181/) (2026)
- [Decompose, Compare, and Decide: Multimodal LLMs are Implicit Few-Shot Learners](https://mlsanity.com/paper/2607.00125/) (2026)
- [TALSC: Timeliness-Aware Large-Small VLM Collaboration for Infrastructure-Assisted Autonomous Driving](https://mlsanity.com/paper/2608.01998/) (2026)

## Abstract (arXiv)

Few-shot classification (FSC) is a fundamental yet challenging task in computer vision that involves recognizing novel classes from limited data. While previous methods have focused on enhancing visual features or incorporating additional modalities, Large Vision Language Models (LVLMs) offer a promising alternative due to their rich knowledge and strong visual perception. However, LVLMs risk learning specific response formats rather than effectively extracting useful information from support data in FSC tasks. In this paper, we investigate LVLMs' performance in FSC and identify key issues such as insufficient learning and the presence of severe positional biases. To tackle the above challenges, we adopt the meta-learning strategy to teach models "learn to learn". By constructing a rich set of meta-tasks for instruction fine-tuning, LVLMs enhance the ability to extract information from few-shot support data for classification. Additionally, we further boost LVLM's few-shot learning capabilities through label augmentation and candidate selection in the fine-tuning and inference stage, respectively. Label augmentation is implemented via a character perturbation strategy to ensure the model focuses on support information. Candidate selection leverages attribute descriptions to filter out unreliable candidates and simplify the task. Extensive experiments demonstrate that our approach achieves superior performance on both general and fine-grained datasets. Furthermore, our candidate selection strategy has been proven beneficial for training-free LVLMs.