# TransMed: Large Language Models Enhance Vision Transformer for Biomedical Image Classification

arXiv: https://arxiv.org/abs/2312.07125 · HTML: https://mlsanity.com/paper/2312.07125/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 34 of its 39 references that are in the map.
- First posted on arXiv 12 Dec 2023.

## Builds on (most cited first, 30 of 34)

- [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)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [A Closer Look at Few-shot Classification](https://mlsanity.com/paper/1904.04232/) (2019)
- [MedCLIP: Contrastive Learning from Unpaired Medical Images and Text](https://mlsanity.com/paper/2210.10163/) (2022)
- [Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation](https://mlsanity.com/paper/2304.12620/) (2023)
- [Recognize Anything: A Strong Image Tagging Model](https://mlsanity.com/paper/2306.03514/) (2023)
- [A Baseline for Few-Shot Image Classification](https://mlsanity.com/paper/1909.02729/) (2019)
- [AdapterDrop: On the Efficiency of Adapters in Transformers](https://mlsanity.com/paper/2010.11918/) (2020)
- [PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents](https://mlsanity.com/paper/2303.07240/) (2023)
- [DaViT: Dual Attention Vision Transformers](https://mlsanity.com/paper/2204.03645/) (2022)
- [Visual Language Pretrained Multiple Instance Zero-Shot Transfer for Histopathology Images](https://mlsanity.com/paper/2306.07831/) (2023)
- [Knowledge-enhanced Visual-Language Pre-training on Chest Radiology Images](https://mlsanity.com/paper/2302.14042/) (2023)
- [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)
- [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)
- [Partial Is Better Than All: Revisiting Fine-tuning Strategy for Few-shot Learning](https://mlsanity.com/paper/2102.03983/) (2021)
- [What Makes Transfer Learning Work For Medical Images: Feature Reuse & Other Factors](https://mlsanity.com/paper/2203.01825/) (2022)
- [Few-shot Medical Image Segmentation using a Global Correlation Network with Discriminative Embedding](https://mlsanity.com/paper/2012.05440/) (2020)
- [Text-guided Foundation Model Adaptation for Pathological Image Classification](https://mlsanity.com/paper/2307.14901/) (2023)
- [A Closer Look at Few-shot Classification Again](https://mlsanity.com/paper/2301.12246/) (2023)
- [Semantic Prompt for Few-Shot Image Recognition](https://mlsanity.com/paper/2303.14123/) (2023)

## Abstract (arXiv)

Few-shot learning has been studied to adapt models to tasks with very few samples. It holds profound significance, particularly in clinical tasks, due to the high annotation cost of medical images. Several works have explored few-shot learning on medical images, yet they still require a large number of medical images for pre-training models to gain domain-specific priors. Vision foundation models recently have achieved remarkable success in natural images. Hence, adapting rapidly advancing vision foundation models from natural images to few-shot clinical tasks holds great promise. MedFMC has recently organized a challenge to shed more light on this topic at NeurIPS 2023. In this work, we present our challenge solution. We observe that a simple variant of fine-tuning with partial freezing shows remarkable performance. Empirical evidence demonstrates that this approach could outperform various common fine-tuning methods under limited sample sizes. Additionally, we explore enhanced utilization of semantic supervision to boost performance. We propose a novel approach that contextualizes labels via large language models (LLMs). Our findings reveal that the context generated by LLMs significantly enhances the discrimination of semantic embeddings for similar categories, resulting in a notable performance improvement of 3%-5% in 1-shot settings compared to commonly employed one-hot labels and other semantic supervision methods. Our solution secures the 1st place in the MedFMC challenge.