# FrozenSeg: Harmonizing Frozen Foundation Models for Open-Vocabulary Segmentation

arXiv: https://arxiv.org/abs/2409.03525 · HTML: https://mlsanity.com/paper/2409.03525/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 50 references that are in the map.
- First posted on arXiv 5 Sep 2024.

## Builds on (most cited first, 30 of 44)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Microsoft COCO Captions: Data Collection and Evaluation Server](https://mlsanity.com/paper/1504.00325/) (2015)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks](https://mlsanity.com/paper/2401.14159/) (2024)
- [Exploring Plain Vision Transformer Backbones for Object Detection](https://mlsanity.com/paper/2203.16527/) (2022)
- [Detecting Twenty-thousand Classes using Image-level Supervision](https://mlsanity.com/paper/2201.02605/) (2022)
- [DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR](https://mlsanity.com/paper/2201.12329/) (2022)
- [Vision Transformer Adapter for Dense Predictions](https://mlsanity.com/paper/2205.08534/) (2022)
- [Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP](https://mlsanity.com/paper/2210.04150/) (2022)
- [Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling](https://mlsanity.com/paper/2111.03930/) (2021)
- [Conditional DETR for Fast Training Convergence](https://mlsanity.com/paper/2108.06152/) (2021)
- [Segment Anything in High Quality](https://mlsanity.com/paper/2306.01567/) (2023)
- [Faster Segment Anything: Towards Lightweight SAM for Mobile Applications](https://mlsanity.com/paper/2306.14289/) (2023)
- [Side Adapter Network for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2302.12242/) (2023)
- [A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model](https://mlsanity.com/paper/2112.14757/) (2021)
- [Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP](https://mlsanity.com/paper/2308.02487/) (2023)

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

- [DeCLIP: Decoupled Learning for Open-Vocabulary Dense Perception](https://mlsanity.com/paper/2505.04410/) (2025)
- [Vision-Language Model for Object Detection and Segmentation: A Review and Evaluation](https://mlsanity.com/paper/2504.09480/) (2025)
- [Generalized Decoupled Learning for Enhancing Open-Vocabulary Dense Perception](https://mlsanity.com/paper/2508.11256/) (2025)
- [SAM-MI: A Mask-Injected Framework for Enhancing Open-Vocabulary Semantic Segmentation with SAM](https://mlsanity.com/paper/2511.20027/) (2025)
- [Federated EndoViT: Pretraining Vision Transformers via Federated Learning on Endoscopic Image Collections](https://mlsanity.com/paper/2504.16612/) (2025)
- [EOVSAM: Efficient Open-Vocabulary Segmentation with SAM 3 in One Pass](https://mlsanity.com/paper/2608.02284/) (2026)
- [TAG: Calibrating SAM3 for Universal Image Segmentation without Dense Supervision](https://mlsanity.com/paper/2610.14651/) (2026)

## Abstract (arXiv)

Open-vocabulary segmentation poses significant challenges, as it requires segmenting and recognizing objects across an open set of categories in unconstrained environments. Building on the success of powerful vision-language (ViL) foundation models, such as CLIP, recent efforts sought to harness their zero-short capabilities to recognize unseen categories. Despite notable performance improvements, these models still encounter the critical issue of generating precise mask proposals for unseen categories and scenarios, resulting in inferior segmentation performance eventually. To address this challenge, we introduce a novel approach, FrozenSeg, designed to integrate spatial knowledge from a localization foundation model (e.g., SAM) and semantic knowledge extracted from a ViL model (e.g., CLIP), in a synergistic framework. Taking the ViL model's visual encoder as the feature backbone, we inject the space-aware feature into the learnable queries and CLIP features within the transformer decoder. In addition, we devise a mask proposal ensemble strategy for further improving the recall rate and mask quality. To fully exploit pre-trained knowledge while minimizing training overhead, we freeze both foundation models, focusing optimization efforts solely on a lightweight transformer decoder for mask proposal generation-the performance bottleneck. Extensive experiments demonstrate that FrozenSeg advances state-of-the-art results across various segmentation benchmarks, trained exclusively on COCO panoptic data, and tested in a zero-shot manner. Code is available at https://github.com/chenxi52/FrozenSeg.