mlsanityData to 7 Oct 2026

CalibCLIP: Contextual Calibration of Dominant Semantics for Text-Driven Image Retrieval

arXiv 2510.05586 ↗First posted 7 Oct 2025cs.CVcited by 3

On the map: Multimodal LLMs / vision-language models → Document understanding and multimodal RAG

Abstract (arXiv)

Existing Visual Language Models (VLMs) suffer structural limitations where a few low contribution tokens may excessively capture global semantics, dominating the information aggregation process and suppressing the discriminative features in text-driven image retrieval tasks. To address this, we introduce CalibCLIP, a training-free method designed to calibrate the suppressive effect of dominant tokens. Specifically, in the visual space, we propose the Contrastive Visual Enhancer (CVE), which decouples visual features into target and low information regions. Subsequently, it identifies dominant tokens and dynamically suppresses their representations.In the textual space, we introduce the Discriminative Concept Calibrator (DCC), which aims to differentiate between general and discriminative concepts within the text query. By mitigating the challenges posed by generic concepts and improving the representations of discriminative concepts, DCC strengthens the differentiation among similar samples. Finally, extensive experiments demonstrate consistent improvements across seven benchmarks spanning three image retrieval tasks, underscoring the effectiveness of CalibCLIP. Code is available at: https://github.com/kangbin98/CalibCLIP

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Document understanding and multimodal RAG, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 36 of its 68 references that are in the map. First posted on arXiv 7 Oct 2025.

Builds on

36 of 68 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025ImageScope: Unifying Language-Guided Image Retrieval via Large Multimodal Model Collective Reasoning13 Mar
  2. 2024Enhancing Interactive Image Retrieval With Query Rewriting Using Large Language Models and Vision Language Models29 Apr

Other references · 34

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,337
  5. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,534
  6. 2021Align before Fuse: Vision and Language Representation Learning with Momentum Distillationcited by 1,612
  7. 2023Vision-Language Models for Vision Tasks: A Surveycited by 834
  8. 2023VILA: On Pre-training for Visual Language Modelscited by 686
  9. 2024What matters when building vision-language models?cited by 321
  10. 2021Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Modelscited by 244
  11. 2017Person Search with Natural Language Descriptioncited by 149
  12. 2023SSR-Encoder: Encoding Selective Subject Representation for Subject-Driven Generationcited by 142
22 more
  1. 2020Learning the Best Pooling Strategy for Visual Semantic Embeddingcited by 136
  2. 2023Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrievalcited by 131
  3. 2021Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identificationcited by 108
  4. 2021DSSL: Deep Surroundings-person Separation Learning for Text-based Person Retrievalcited by 102
  5. 2022ARTEMIS: Attention-based Retrieval with Text-Explicit Matching and Implicit Similaritycited by 82
  6. 2023Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmarkcited by 75
  7. 2022See Finer, See More: Implicit Modality Alignment for Text-based Person Retrievalcited by 65
  8. 2024Explore the Potential of CLIP for Training-Free Open Vocabulary Semantic Segmentationcited by 61
  9. 2024CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matchingcited by 60
  10. 2023Sentence-level Prompts Benefit Composed Image Retrievalcited by 59
  11. 2023COLA: A Benchmark for Compositional Text-to-image Retrievalcited by 53
  12. 2023Composed Image Retrieval using Contrastive Learning and Task-oriented CLIP-based Featurescited by 52
  13. 2023An Empirical Study of CLIP for Text-based Person Searchcited by 38
  14. 2023Candidate Set Re-ranking for Composed Image Retrieval with Dual Multi-modal Encodercited by 35
  15. 2023Self-Training Boosted Multi-Factor Matching Network for Composed Image Retrievalcited by 22
  16. 2024CaLa: Complementary Association Learning for Augmenting Composed Image Retrievalcited by 21
  17. 2024Improving Composed Image Retrieval via Contrastive Learning with Scaling Positives and Negativescited by 20
  18. 2024Separating the "Chirp" from the "Chat": Self-supervised Visual Grounding of Sound and Languagecited by 17
  19. 2023Invisible Relevance Bias: Text-Image Retrieval Models Prefer AI-Generated Imagescited by 13
  20. 2024You'll Never Walk Alone: A Sketch and Text Duet for Fine-Grained Image Retrievalcited by 12
  21. 2023NEUCORE: Neural Concept Reasoning for Composed Image Retrievalcited by 8
  22. 2023Contrastive Transformer Learning with Proximity Data Generation for Text-Based Person Searchcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025Less Is More, but Where? Dynamic Token Compression via LLM-Guided Keyframe Priorcited by 15
  2. 2026Towards Highly Transferable Vision-Language Attack via Semantic-Augmented Dynamic Contrastive Interactioncited by 0
  3. 2026PrecogUI: Proactive GUI Agents via Pre-cognitive Simulation and Experience Retrievalcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Seeing Through Words: Controlling Visual Retrieval Quality with Language Models
  2. 2025Vision-Free Retrieval: Rethinking Multimodal Search with Textual Scene Descriptions
  3. 2025VisRet: Visualization Improves Knowledge-Intensive Text-to-Image Retrieval
  4. 2025ABC: Achieving Better Control of Multimodal Embeddings using VLMs
  5. 2025A Little More Like This: Text-to-Image Retrieval with Vision-Language Models Using Relevance Feedback
  6. 2026Concepts Complement Dense Semantics: Learning Compact Sparse Spaces for Text-Image Retrieval
  7. 2026Human-Grounded Calibration for Long-Text Image-Text Congruence in Vision-Language Models
  8. 2024VISTA: Visualized Text Embedding For Universal Multi-Modal Retrieval