mlsanityData to 14 Oct 2026

Representation Discrepancy Bridging Method for Remote Sensing Image-Text Retrieval

arXiv 2505.16756 ↗First posted 22 May 2025cs.CV cs.IR cs.MMcited by 1

Not on the map. Why?

Abstract (arXiv)

Remote Sensing Image-Text Retrieval (RSITR) plays a critical role in geographic information interpretation, disaster monitoring, and urban planning by establishing semantic associations between image and textual descriptions. Existing Parameter-Efficient Fine-Tuning (PEFT) methods for Vision-and-Language Pre-training (VLP) models typically adopt symmetric adapter structures for exploring cross-modal correlations. However, the strong discriminative nature of text modality may dominate the optimization process and inhibits image representation learning. The nonnegligible imbalanced cross-modal optimization remains a bottleneck to enhancing the model performance. To address this issue, this study proposes a Representation Discrepancy Bridging (RDB) method for the RSITR task. On the one hand, a Cross-Modal Asymmetric Adapter (CMAA) is designed to enable modality-specific optimization and improve feature alignment. The CMAA comprises a Visual Enhancement Adapter (VEA) and a Text Semantic Adapter (TSA). VEA mines fine-grained image features by Differential Attention (DA) mechanism, while TSA identifies key textual semantics through Hierarchical Attention (HA) mechanism. On the other hand, this study extends the traditional single-task retrieval framework to a dual-task optimization framework and develops a Dual-Task Consistency Loss (DTCL). The DTCL improves cross-modal alignment robustness through an adaptive weighted combination of cross-modal, classification, and exponential moving average consistency constraints. Experiments on RSICD and RSITMD datasets show that the proposed RDB method achieves a 6%-11% improvement in mR metrics compared to state-of-the-art PEFT methods and a 1.15%-2% improvement over the full fine-tuned GeoRSCLIP model.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 28 of its 53 references that are in the map. First posted on arXiv 22 May 2025.

Builds on

28 of 53 references.

References · 28

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,322
  3. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
  4. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,915
  5. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
  6. 2019ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Taskscited by 2,222
  7. 2022Visual Prompt Tuningcited by 1,681
  8. 2021ViLT: Vision-and-Language Transformer Without Convolution or Region Supervisioncited by 1,230
  9. 2021CLIP-Adapter: Better Vision-Language Models with Feature Adapterscited by 1,026
  10. 2022AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognitioncited by 719
  11. 2022MaPLe: Multi-modal Prompt Learningcited by 687
  12. 2021SimVLM: Simple Visual Language Model Pretraining with Weak Supervisioncited by 647
16 more
  1. 2023RemoteCLIP: A Vision Language Foundation Model for Remote Sensingcited by 363
  2. 2020ERNIE-ViL: Knowledge Enhanced Vision-Language Representations Through Scene Graphcited by 211
  3. 2017Exploring Models and Data for Remote Sensing Image Caption Generationcited by 197
  4. 2020TDN: Temporal Difference Networks for Efficient Action Recognitioncited by 183
  5. 2015Ask Me Anything: Dynamic Memory Networks for Natural Language Processingcited by 117
  6. 2018Auxiliary Tasks in Multi-task Learningcited by 108
  7. 2021M6: A Chinese Multimodal Pretrainercited by 91
  8. 2022Exploring a Fine-Grained Multiscale Method for Cross-Modal Remote Sensing Image Retrievalcited by 77
  9. 2022Remote Sensing Cross-Modal Text-Image Retrieval Based on Global and Local Informationcited by 40
  10. 2023UniAdapter: Unified Parameter-Efficient Transfer Learning for Cross-modal Modelingcited by 40
  11. 2022Positive-incentive Noisecited by 39
  12. 2022Cross-Modal Adapter for Vision-Language Retrievalcited by 35
  13. 2023Parameter-Efficient Transfer Learning for Remote Sensing Image-Text Retrievalcited by 24
  14. 2019Matching Images and Text with Multi-modal Tensor Fusion and Re-rankingcited by 20
  15. 2021Semantics-Consistent Representation Learning for Remote Sensing Image-Voice Retrievalcited by 8
  16. 2024Pushing the Limits of Vision-Language Models in Remote Sensing without Human Annotationscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026DARAD: Dual Adapters and Ranking-Aware Distillation for Continual Remote Sensing Image-Text Retrievalcited by 0