# Rewrite Caption Semantics: Bridging Semantic Gaps for Language-Supervised Semantic Segmentation

arXiv: https://arxiv.org/abs/2309.13505 · HTML: https://mlsanity.com/paper/2309.13505/

## Key facts

- Cited by 21 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 43 of its 52 references that are in the map.
- First posted on arXiv 24 Sep 2023.

## 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 43)

- [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)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts](https://mlsanity.com/paper/2102.08981/) (2021)
- [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://mlsanity.com/paper/2107.06278/) (2021)
- [COCO-Stuff: Thing and Stuff Classes in Context](https://mlsanity.com/paper/1612.03716/) (2016)
- [Vision-Language Models for Vision Tasks: A Survey](https://mlsanity.com/paper/2304.00685/) (2023)
- [PaLI: A Jointly-Scaled Multilingual Language-Image Model](https://mlsanity.com/paper/2209.06794/) (2022)
- [Language-driven Semantic Segmentation](https://mlsanity.com/paper/2201.03546/) (2022)
- [FILIP: Fine-grained Interactive Language-Image Pre-Training](https://mlsanity.com/paper/2111.07783/) (2021)
- [Extract Free Dense Labels from CLIP](https://mlsanity.com/paper/2112.01071/) (2021)
- [Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP](https://mlsanity.com/paper/2210.04150/) (2022)
- [GroupViT: Semantic Segmentation Emerges from Text Supervision](https://mlsanity.com/paper/2202.11094/) (2022)
- [Scaling Open-Vocabulary Image Segmentation with Image-Level Labels](https://mlsanity.com/paper/2112.12143/) (2021)
- [SLIP: Self-supervision meets Language-Image Pre-training](https://mlsanity.com/paper/2112.12750/) (2021)
- [Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm](https://mlsanity.com/paper/2110.05208/) (2021)
- [Side Adapter Network for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2302.12242/) (2023)
- [Generalized Decoding for Pixel, Image, and Language](https://mlsanity.com/paper/2212.11270/) (2022)
- [Zero-Shot Semantic Segmentation](https://mlsanity.com/paper/1906.00817/) (2019)
- [A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model](https://mlsanity.com/paper/2112.14757/) (2021)

## Built on by (most cited first, 21 of 21)

- [ClearCLIP: Decomposing CLIP Representations for Dense Vision-Language Inference](https://mlsanity.com/paper/2407.12442/) (2024)
- [ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation](https://mlsanity.com/paper/2408.04883/) (2024)
- [DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment](https://mlsanity.com/paper/2412.16334/) (2024)
- [CorrCLIP: Reconstructing Patch Correlations in CLIP for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2411.10086/) (2024)
- [ResCLIP: Residual Attention for Training-free Dense Vision-language Inference](https://mlsanity.com/paper/2411.15851/) (2024)
- [Image-Text Co-Decomposition for Text-Supervised Semantic Segmentation](https://mlsanity.com/paper/2404.04231/) (2024)
- [CLIPer: Hierarchically Improving Spatial Representation of CLIP for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2411.13836/) (2024)
- [ReME: A Data-Centric Framework for Training-Free Open-Vocabulary Segmentation](https://mlsanity.com/paper/2506.21233/) (2025)
- [Training-Free Class Purification for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2508.00557/) (2025)
- [ReCLIP++: Learn to Rectify the Bias of CLIP for Unsupervised Semantic Segmentation](https://mlsanity.com/paper/2408.06747/) (2024)
- [TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification](https://mlsanity.com/paper/2312.14149/) (2023)
- [TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias](https://mlsanity.com/paper/2404.00384/) (2024)
- [Multi-Grained Cross-modal Alignment for Learning Open-vocabulary Semantic Segmentation from Text Supervision](https://mlsanity.com/paper/2403.03707/) (2024)
- [Rethinking the Global Knowledge of CLIP in Training-Free Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2502.06818/) (2025)
- [Native Segmentation Vision Transformers](https://mlsanity.com/paper/2505.16993/) (2025)
- [VIP: Visual-guided Prompt Evolution for Efficient Dense Vision-Language Inference](https://mlsanity.com/paper/2605.12325/) (2026)
- [Improving Visual Discriminability of CLIP for Training-Free Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2510.23894/) (2025)
- [Handling Imbalanced Pseudolabels for Vision-Language Models with Concept Alignment and Confusion-Aware Calibrated Margin](https://mlsanity.com/paper/2505.02056/) (2025)
- [SynSeg: Feature Synergy for Multi-Category Contrastive Learning in End-to-End Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2508.06115/) (2025)
- [OV-Stitcher: A Global Context-Aware Framework for Training-Free Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2604.08110/) (2026)
- [Perceptual Anchoring: Prototype-Guided Text Calibration for Training-free Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2608.03991/) (2026)

## Abstract (arXiv)

Vision-Language Pre-training has demonstrated its remarkable zero-shot recognition ability and potential to learn generalizable visual representations from language supervision. Taking a step ahead, language-supervised semantic segmentation enables spatial localization of textual inputs by learning pixel grouping solely from image-text pairs. Nevertheless, the state-of-the-art suffers from clear semantic gaps between visual and textual modality: plenty of visual concepts appeared in images are missing in their paired captions. Such semantic misalignment circulates in pre-training, leading to inferior zero-shot performance in dense predictions due to insufficient visual concepts captured in textual representations. To close such semantic gap, we propose Concept Curation (CoCu), a pipeline that leverages CLIP to compensate for the missing semantics. For each image-text pair, we establish a concept archive that maintains potential visually-matched concepts with our proposed vision-driven expansion and text-to-vision-guided ranking. Relevant concepts can thus be identified via cluster-guided sampling and fed into pre-training, thereby bridging the gap between visual and textual semantics. Extensive experiments over a broad suite of 8 segmentation benchmarks show that CoCu achieves superb zero-shot transfer performance and greatly boosts language-supervised segmentation baseline by a large margin, suggesting the value of bridging semantic gap in pre-training data.