# LMSeg: Language-guided Multi-dataset Segmentation

arXiv: https://arxiv.org/abs/2302.13495 · HTML: https://mlsanity.com/paper/2302.13495/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 42 references that are in the map.
- First posted on arXiv 27 Feb 2023.

## 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)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers](https://mlsanity.com/paper/2012.15840/) (2020)
- [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://mlsanity.com/paper/2107.06278/) (2021)
- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)
- [Dual Attention Network for Scene Segmentation](https://mlsanity.com/paper/1809.02983/) (2018)
- [COCO-Stuff: Thing and Stuff Classes in Context](https://mlsanity.com/paper/1612.03716/) (2016)
- [Segmenter: Transformer for Semantic Segmentation](https://mlsanity.com/paper/2105.05633/) (2021)
- [Focal Loss for Dense Object Detection](https://mlsanity.com/paper/1708.02002/) (2017)
- [CCNet: Criss-Cross Attention for Semantic Segmentation](https://mlsanity.com/paper/1811.11721/) (2018)
- [DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting](https://mlsanity.com/paper/2112.01518/) (2021)
- [Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling](https://mlsanity.com/paper/2111.03930/) (2021)
- [MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers](https://mlsanity.com/paper/2012.00759/) (2020)
- [Simple multi-dataset detection](https://mlsanity.com/paper/2102.13086/) (2021)
- [MSeg: A Composite Dataset for Multi-domain Semantic Segmentation](https://mlsanity.com/paper/2112.13762/) (2021)
- [Object Detection with a Unified Label Space from Multiple Datasets](https://mlsanity.com/paper/2008.06614/) (2020)
- [Cross-Dataset Collaborative Learning for Semantic Segmentation in Autonomous Driving](https://mlsanity.com/paper/2103.11351/) (2021)

## Built on by (most cited first, 15 of 15)

- [Transformer-Based Visual Segmentation: A Survey](https://mlsanity.com/paper/2304.09854/) (2023)
- [Explore the Potential of CLIP for Training-Free Open Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2407.08268/) (2024)
- [DaTaSeg: Taming a Universal Multi-Dataset Multi-Task Segmentation Model](https://mlsanity.com/paper/2306.01736/) (2023)
- [Matting Anything](https://mlsanity.com/paper/2306.05399/) (2023)
- [Multi-Space Alignments Towards Universal LiDAR Segmentation](https://mlsanity.com/paper/2405.01538/) (2024)
- [Open Panoramic Segmentation](https://mlsanity.com/paper/2407.02685/) (2024)
- [Towards Open-Ended Visual Recognition with Large Language Model](https://mlsanity.com/paper/2311.08400/) (2023)
- [AIMS: All-Inclusive Multi-Level Segmentation](https://mlsanity.com/paper/2305.17768/) (2023)
- [Open-Vocabulary Semantic Part Segmentation of 3D Human](https://mlsanity.com/paper/2502.19782/) (2025)
- [Bridging Annotation Gaps: Transferring Labels to Align Object Detection Datasets](https://mlsanity.com/paper/2506.04737/) (2025)
- [Mixed-Query Transformer: A Unified Image Segmentation Architecture](https://mlsanity.com/paper/2404.04469/) (2024)
- [Automated Label Unification for Multi-Dataset Semantic Segmentation with GNNs](https://mlsanity.com/paper/2407.10534/) (2024)
- [Resolving Inconsistent Semantics in Multi-Dataset Image Segmentation](https://mlsanity.com/paper/2409.09893/) (2024)
- [A Semantic Space is Worth 256 Language Descriptions: Make Stronger Segmentation Models with Descriptive Properties](https://mlsanity.com/paper/2312.13764/) (2023)
- [AdaSemSeg: An Adaptive Few-shot Semantic Segmentation of Seismic Facies](https://mlsanity.com/paper/2501.16760/) (2025)

## Abstract (arXiv)

It's a meaningful and attractive topic to build a general and inclusive segmentation model that can recognize more categories in various scenarios. A straightforward way is to combine the existing fragmented segmentation datasets and train a multi-dataset network. However, there are two major issues with multi-dataset segmentation: (1) the inconsistent taxonomy demands manual reconciliation to construct a unified taxonomy; (2) the inflexible one-hot common taxonomy causes time-consuming model retraining and defective supervision of unlabeled categories. In this paper, we investigate the multi-dataset segmentation and propose a scalable Language-guided Multi-dataset Segmentation framework, dubbed LMSeg, which supports both semantic and panoptic segmentation. Specifically, we introduce a pre-trained text encoder to map the category names to a text embedding space as a unified taxonomy, instead of using inflexible one-hot label. The model dynamically aligns the segment queries with the category embeddings. Instead of relabeling each dataset with the unified taxonomy, a category-guided decoding module is designed to dynamically guide predictions to each datasets taxonomy. Furthermore, we adopt a dataset-aware augmentation strategy that assigns each dataset a specific image augmentation pipeline, which can suit the properties of images from different datasets. Extensive experiments demonstrate that our method achieves significant improvements on four semantic and three panoptic segmentation datasets, and the ablation study evaluates the effectiveness of each component.