mlsanityData to 14 Oct 2026

CPSeg: Finer-grained Image Semantic Segmentation via Chain-of-Thought Language Prompting

arXiv 2310.16069 ↗First posted 24 Oct 2023cs.CVcited by 28

On the map: LLM reasoning → Multimodal reasoning

Abstract (arXiv)

Natural scene analysis and remote sensing imagery offer immense potential for advancements in large-scale language-guided context-aware data utilization. This potential is particularly significant for enhancing performance in downstream tasks such as object detection and segmentation with designed language prompting. In light of this, we introduce the CPSeg, Chain-of-Thought Language Prompting for Finer-grained Semantic Segmentation), an innovative framework designed to augment image segmentation performance by integrating a novel "Chain-of-Thought" process that harnesses textual information associated with images. This groundbreaking approach has been applied to a flood disaster scenario. CPSeg encodes prompt texts derived from various sentences to formulate a coherent chain-of-thought. We propose a new vision-language dataset, FloodPrompt, which includes images, semantic masks, and corresponding text information. This not only strengthens the semantic understanding of the scenario but also aids in the key task of semantic segmentation through an interplay of pixel and text matching maps. Our qualitative and quantitative analyses validate the effectiveness of CPSeg.

Key facts. Cited by 28 papers in the map (data through 14 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 32 of its 40 references that are in the map. First posted on arXiv 24 Oct 2023.

Builds on

32 of 40 references.

References · 32

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  5. 2022Generative Adversarial Networkscited by 5,627
  6. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  7. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  8. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,386
  9. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,270
  10. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  11. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  12. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
20 more
  1. 2015VQA: Visual Question Answeringcited by 2,506
  2. 2016Pyramid Scene Parsing Networkcited by 2,479
  3. 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,423
  4. 2017Revisiting Unreasonable Effectiveness of Data in Deep Learning Eracited by 919
  5. 2022Language-driven Semantic Segmentationcited by 717
  6. 2021DenseCLIP: Language-Guided Dense Prediction with Context-Aware Promptingcited by 532
  7. 2020Dense Contrastive Learning for Self-Supervised Visual Pre-Trainingcited by 512
  8. 2021Scaling Open-Vocabulary Image Segmentation with Image-Level Labelscited by 473
  9. 2016ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentationcited by 291
  10. 2021LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentationcited by 261
  11. 2019Zero-Shot Semantic Segmentationcited by 245
  12. 2021A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Modelcited by 223
  13. 2020FloodNet: A High Resolution Aerial Imagery Dataset for Post Flood Scene Understandingcited by 181
  14. 2022Open-world Semantic Segmentation via Contrasting and Clustering Vision-Language Embeddingcited by 67
  15. 2022Mask-FPAN: Semi-Supervised Face Parsing in the Wild With De-Occlusion and UV GANcited by 16
  16. 2023IFSeg: Image-free Semantic Segmentation via Vision-Language Modelcited by 15
  17. 2021Deep Learning Based 3D Point Cloud Regression for Estimating Forest Biomasscited by 12
  18. 2022LR-CSNet: Low-Rank Deep Unfolding Network for Image Compressive Sensingcited by 6
  19. 2023BuildSeg: A General Framework for the Segmentation of Buildingscited by 6
  20. 2023Edge Aware Learning for 3D Point Cloudcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 15; 2025: 11; 2026: 2.

28 papers.

Sort:

By area:

  1. 2025Multimodal Chain-of-Thought Reasoning: A Comprehensive Surveycited by 182
  2. 2024Exploring Diverse Methods in Visual Question Answeringcited by 45
  3. 2024Regional Style and Color Transfercited by 30
  4. 2024Human Motion Instruction Tuningcited by 29
  5. 2024The Role of Deductive and Inductive Reasoning in Large Language Modelscited by 20
  6. 2024Rumor Detection with a novel graph neural network approachcited by 15
  7. 2025CountLLM: Towards Generalizable Repetitive Action Counting via Large Language Modelcited by 14
  8. 2025LISAT: Language-Instructed Segmentation Assistant for Satellite Imagerycited by 13
  9. 2024CAS-ViT: Convolutional Additive Self-attention Vision Transformers for Efficient Mobile Applicationscited by 12
  10. 2025UORA: Uniform Orthogonal Reinitialization Adaptation in Parameter-Efficient Fine-Tuning of Large Modelscited by 11
  11. 2024Advanced User Credit Risk Prediction Model using LightGBM, XGBoost and Tabnet with SMOTEENNcited by 10
  12. 2025Self-Destructive Language Modelcited by 10
16 more
  1. 2025Reasoning or Retrieval? A Study of Answer Attribution on Large Reasoning Modelscited by 10
  2. 2024Mapping New Realities: Ground Truth Image Creation with Pix2Pix Image-to-Image Translationcited by 7
  3. 2025DescribeEarth: Describe Anything for Remote Sensing Imagescited by 5
  4. 2024You Only Speak Once to Seecited by 4
  5. 2025Is Meta-Learning Out? Rethinking Unsupervised Few-Shot Classification with Limited Entropycited by 4
  6. 2026PSGS: Text-driven Panorama Sliding Scene Generation via Gaussian Splattingcited by 4
  7. 2025OrderChain: Towards General Instruct-Tuning for Stimulating the Ordinal Understanding Ability of MLLMcited by 3
  8. 2025Debate-Enhanced Pseudo Labeling and Frequency-Aware Progressive Debiasing for Weakly-Supervised Camouflaged Object Detection with Scribble Annotationscited by 3
  9. 2024End-To-End Training and Testing Gamification Framework to Learn Human Highway Drivingcited by 2
  10. 2024Tree Counting by Bridging 3D Point Clouds with Imagerycited by 1
  11. 2024CPA-Enhancer: Chain-of-Thought Prompted Adaptive Enhancer for Object Detection under Unknown Degradationscited by 1
  12. 2024Advancements in Visual Language Models for Remote Sensing: Datasets, Capabilities, and Enhancement Techniquescited by 1
  13. 2025CNSocialDepress: A Chinese Social Media Dataset for Depression Risk Detection and Structured Analysiscited by 1
  14. 2024MedFLIP: Medical Vision-and-Language Self-supervised Fast Pre-Training with Masked Autoencodercited by 0
  15. 2024International Trade Flow Prediction with Bilateral Trade Provisionscited by 0
  16. 2026Grounding Multi-Hop Reasoning in Structural Causal Models via Group Relative Policy Optimizationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Towards Training-free Open-world Segmentation via Image Prompt Foundation Models
  2. 2025SegEarth-R2: Towards Comprehensive Language-guided Segmentation for Remote Sensing Images
  3. 2025Show or Tell? Effectively prompting Vision-Language Models for semantic segmentation
  4. 2026Toward Semantic-Agnostic and Shape-Aware Vision-Language Segmentation Models
  5. 2026VPRef: A Cross-Domain Benchmark for Referring Remote Sensing Image Segmentation
  6. 2026Enabling Training-Free Text-Based Remote Sensing Segmentation
  7. 2026Urban Socio-Semantic Segmentation with Vision-Language Reasoning
  8. 2023Neural Implicit Vision-Language Feature Fields