# MGRL-RSCC: Multi-Granularity Reward Reinforcement Learning for Fine-Grained Remote Sensing Change Captioning

arXiv: https://arxiv.org/abs/2609.26166 · HTML: https://mlsanity.com/paper/2609.26166/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL training of language and agent models, one of 15 directions in Deep reinforcement learning methods.
- Builds on 30 of its 55 references that are in the map.
- First posted on arXiv 9 Aug 2026.

## Placed in

- Deep reinforcement learning methods / [RL training of language and agent models](https://mlsanity.com/deeprl/rl-training-of-language-and-agent-models/)

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

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks](https://mlsanity.com/paper/1506.03099/) (2015)
- [Self-critical Sequence Training for Image Captioning](https://mlsanity.com/paper/1612.00563/) (2016)
- [Auto-Encoding Scene Graphs for Image Captioning](https://mlsanity.com/paper/1812.02378/) (2018)
- [Describing and Localizing Multiple Changes with Transformers](https://mlsanity.com/paper/2103.14146/) (2021)
- [Changes to Captions: An Attentive Network for Remote Sensing Change Captioning](https://mlsanity.com/paper/2304.01091/) (2023)
- [CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning](https://mlsanity.com/paper/2509.22647/) (2025)
- [RSCaMa: Remote Sensing Image Change Captioning with State Space Model](https://mlsanity.com/paper/2404.18895/) (2024)
- [In Defense of Scene Graphs for Image Captioning](https://mlsanity.com/paper/2102.04990/) (2021)
- [Progressive Scale-aware Network for Remote sensing Image Change Captioning](https://mlsanity.com/paper/2303.00355/) (2023)
- [ChangeChat: An Interactive Model for Remote Sensing Change Analysis via Multimodal Instruction Tuning](https://mlsanity.com/paper/2409.08582/) (2024)
- [Semantic-CC: Boosting Remote Sensing Image Change Captioning via Foundational Knowledge and Semantic Guidance](https://mlsanity.com/paper/2407.14032/) (2024)
- [Enhancing Perception of Key Changes in Remote Sensing Image Change Captioning](https://mlsanity.com/paper/2409.12612/) (2024)
- [SC-Captioner: Improving Image Captioning with Self-Correction by Reinforcement Learning](https://mlsanity.com/paper/2508.06125/) (2025)
- [RSCC: A Large-Scale Remote Sensing Change Caption Dataset for Disaster Events](https://mlsanity.com/paper/2509.01907/) (2025)
- [Actor-Critic Sequence Training for Image Captioning](https://mlsanity.com/paper/1706.09601/) (2017)
- [A Lightweight Sparse Focus Transformer for Remote Sensing Image Change Captioning](https://mlsanity.com/paper/2405.06598/) (2024)
- [Mask Approximation Net: A Novel Diffusion Model Approach for Remote Sensing Change Captioning](https://mlsanity.com/paper/2412.19179/) (2024)
- [Robust Change Captioning in Remote Sensing: SECOND-CC Dataset and MModalCC Framework](https://mlsanity.com/paper/2501.10075/) (2025)
- [Towards Comprehensive Interactive Change Understanding in Remote Sensing: A Large-scale Dataset and Dual-granularity Enhanced VLM](https://mlsanity.com/paper/2509.23105/) (2025)
- [CCCaption: Dual-Reward Reinforcement Learning for Complete and Correct Image Captioning](https://mlsanity.com/paper/2602.21655/) (2026)
- [DeltaVLM: Interactive Remote Sensing Image Change Analysis via Instruction-guided Difference Perception](https://mlsanity.com/paper/2507.22346/) (2025)
- [A TextGCN-Based Decoding Approach for Improving Remote Sensing Image Captioning](https://mlsanity.com/paper/2409.18467/) (2024)
- [SAM Guided Semantic and Motion Changed Region Mining for Remote Sensing Change Captioning](https://mlsanity.com/paper/2511.21420/) (2025)
- [A Novel Actor Dual-Critic Model for Remote Sensing Image Captioning](https://mlsanity.com/paper/2010.01999/) (2020)
- [Semantic-Spatial Feature Fusion with Dynamic Graph Refinement for Remote Sensing Image Captioning](https://mlsanity.com/paper/2503.23453/) (2025)
- [DFM: Difference Feature Modeling with Text-Guided Gated Contrastive Loss for Remote Sensing Image Change Captioning](https://mlsanity.com/paper/2606.27410/) (2026)
- [UAV as Urban Construction Change Monitor: A New Benchmark and Change Captioning Model](https://mlsanity.com/paper/2605.04409/) (2026)

## Abstract (arXiv)

Remote Sensing Change Captioning (RSCC), which aims to generate accurate and detailed linguistic descriptions of ground object variations from bi-temporal remote sensing images, is a critical and challenging task in intelligent remote sensing interpretation. The mainstream autoregressive training paradigm faces severe exposure bias and train-test distribution mismatch, resulting in cumulative generation errors. They tend to produce conservative and template-fixed captions while ignoring subtle scene change details. To address these challenges, this paper proposes a novel multi-granularity reward reinforcement learning paradigm, termed MGRL-RSCC. Specifically, we first leverage a CNN and hierarchical self-attention module to extract and enhance visual features from bi-temporal remote sensing images. A Transformer decoder is then utilized to complete visual-to-linguistic translation. Different from existing methods, we design a dual-decoding strategy and a two-stage joint optimization scheme, which combines token-level supervised learning via greedy decoding and multi-granularity reward-driven self-critical reinforcement learning via sampling decoding. We further construct three complementary reward functions covering linguistic fluency, change state consistency, and structural-semantic relevance to comprehensively optimize caption quality and alleviate false and missing change descriptions. Extensive experiments on multiple public RSCC benchmark datasets demonstrate that the proposed MGRL-RSCC effectively mitigates exposure bias and conservative generation problems in traditional autoregressive methods. The source code and pre-trained models will be released on https://github.com/Event-AHU/MGRL-RSCC