# Universal Medical Image Representation Learning with Compositional Decoders

arXiv: https://arxiv.org/abs/2409.19890 · HTML: https://mlsanity.com/paper/2409.19890/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 58 references that are in the map.
- First posted on arXiv 30 Sep 2024.

## Builds on (most cited first, 30 of 33)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [Kvasir-SEG: A Segmented Polyp Dataset](https://mlsanity.com/paper/1911.07069/) (2019)
- [MedCLIP: Contrastive Learning from Unpaired Medical Images and Text](https://mlsanity.com/paper/2210.10163/) (2022)
- [CoAtNet: Marrying Convolution and Attention for All Data Sizes](https://mlsanity.com/paper/2106.04803/) (2021)
- [Dense Contrastive Learning for Self-Supervised Visual Pre-Training](https://mlsanity.com/paper/2011.09157/) (2020)
- [PraNet: Parallel Reverse Attention Network for Polyp Segmentation](https://mlsanity.com/paper/2006.11392/) (2020)
- [Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks](https://mlsanity.com/paper/2206.08916/) (2022)
- [Pix2seq: A Language Modeling Framework for Object Detection](https://mlsanity.com/paper/2109.10852/) (2021)
- [Generalized Decoding for Pixel, Image, and Language](https://mlsanity.com/paper/2212.11270/) (2022)
- [CLIP-Driven Universal Model for Organ Segmentation and Tumor Detection](https://mlsanity.com/paper/2301.00785/) (2023)
- [A Benchmark for Endoluminal Scene Segmentation of Colonoscopy Images](https://mlsanity.com/paper/1612.00799/) (2016)
- [A Unified Sequence Interface for Vision Tasks](https://mlsanity.com/paper/2206.07669/) (2022)
- [Shallow Attention Network for Polyp Segmentation](https://mlsanity.com/paper/2108.00882/) (2021)
- [SAM on Medical Images: A Comprehensive Study on Three Prompt Modes](https://mlsanity.com/paper/2305.00035/) (2023)
- [TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformers](https://mlsanity.com/paper/2201.05047/) (2022)
- [Medical Image Understanding with Pretrained Vision Language Models: A Comprehensive Study](https://mlsanity.com/paper/2209.15517/) (2022)
- [An Open and Comprehensive Pipeline for Unified Object Grounding and Detection](https://mlsanity.com/paper/2401.02361/) (2024)
- [Large-Vocabulary Segmentation for Medical Images with Text Prompts](https://mlsanity.com/paper/2312.17183/) (2023)
- [Uni-Perceiver v2: A Generalist Model for Large-Scale Vision and Vision-Language Tasks](https://mlsanity.com/paper/2211.09808/) (2022)
- [Med-UniC: Unifying Cross-Lingual Medical Vision-Language Pre-Training by Diminishing Bias](https://mlsanity.com/paper/2305.19894/) (2023)
- [UniSeg: A Prompt-driven Universal Segmentation Model as well as A Strong Representation Learner](https://mlsanity.com/paper/2304.03493/) (2023)
- [SegViTv2: Exploring Efficient and Continual Semantic Segmentation with Plain Vision Transformers](https://mlsanity.com/paper/2306.06289/) (2023)
- [Multi-frame Collaboration for Effective Endoscopic Video Polyp Detection via Spatial-Temporal Feature Transformation](https://mlsanity.com/paper/2107.03609/) (2021)

## Built on by (most cited first, 1 of 1)

- [EndoCogniAgent: Closed-Loop Agentic Reasoning with Self-Consistency Validation for Endoscopic Diagnosis](https://mlsanity.com/paper/2508.07292/) (2025)

## Abstract (arXiv)

Visual-language models have advanced the development of universal models, yet their application in medical imaging remains constrained by specific functional requirements and the limited data. Current general-purpose models are typically designed with task-specific branches and heads, which restricts the shared feature space and the flexibility of model. To address these challenges, we have developed a decomposed-composed universal medical imaging paradigm (UniMed) that supports tasks at all levels. To this end, we first propose a decomposed decoder that can predict two types of outputs -- pixel and semantic, based on a defined input queue. Additionally, we introduce a composed decoder that unifies the input and output spaces and standardizes task annotations across different levels into a discrete token format. The coupled design of these two components enables the model to flexibly combine tasks and mutual benefits. Moreover, our joint representation learning strategy skilfully leverages large amounts of unlabeled data and unsupervised loss, achieving efficient one-stage pretraining for more robust performance. Experimental results show that UniMed achieves state-of-the-art performance on eight datasets across all three tasks and exhibits strong zero-shot and 100-shot transferability. We will release the code and trained models upon the paper's acceptance.