# LBTCap: A Lightweight Bilateral Transformer for Real-Time Remote Sensing Image Change Captioning

arXiv: https://arxiv.org/abs/2607.03320 · HTML: https://mlsanity.com/paper/2607.03320/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 92 references that are in the map.
- First posted on arXiv 3 Jul 2026.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Root Mean Square Layer Normalization](https://mlsanity.com/paper/1910.07467/) (2019)
- [TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Data](https://mlsanity.com/paper/2410.06234/) (2024)
- [Change-Agent: Towards Interactive Comprehensive Remote Sensing Change Interpretation and Analysis](https://mlsanity.com/paper/2403.19646/) (2024)
- [Changes to Captions: An Attentive Network for Remote Sensing Change Captioning](https://mlsanity.com/paper/2304.01091/) (2023)
- [RSCaMa: Remote Sensing Image Change Captioning with State Space Model](https://mlsanity.com/paper/2404.18895/) (2024)
- [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)
- [Remote Sensing SpatioTemporal Vision-Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2412.02573/) (2024)
- [Code-Aligned Autoencoders for Unsupervised Change Detection in Multimodal Remote Sensing Images](https://mlsanity.com/paper/2004.07011/) (2020)
- [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)
- [Pixel-Level Change Detection Pseudo-Label Learning for Remote Sensing Change Captioning](https://mlsanity.com/paper/2312.15311/) (2023)
- [A Lightweight Sparse Focus Transformer for Remote Sensing Image Change Captioning](https://mlsanity.com/paper/2405.06598/) (2024)
- [CDChat: A Large Multimodal Model for Remote Sensing Change Description](https://mlsanity.com/paper/2409.16261/) (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)
- [DeltaVLM: Interactive Remote Sensing Image Change Analysis via Instruction-guided Difference Perception](https://mlsanity.com/paper/2507.22346/) (2025)
- [Towards a multimodal framework for remote sensing image change retrieval and captioning](https://mlsanity.com/paper/2406.13424/) (2024)

## Abstract (arXiv)

Remote sensing image change captioning (RSICC) generates natural-language descriptions of semantic changes between paired remote sensing images (RSIs), supporting applications such as urban planning, disaster response, and environmental monitoring. Although recent methods achieve strong captioning accuracy, most overlook computational efficiency and inference speed, which are essential for real-time deployment in practice. To this end, we propose LBTCap, a lightweight RSICC framework built on a bilateral Transformer that jointly models pre- and post-change features for efficient processing of paired RSIs. Specifically, we introduce a bilateral attention mechanism for paired inputs: the two temporal images are projected into separate queries and keys by the same query and key matrices shared across the two images, the value is formed from their concatenation, and the two resulting attention maps are combined by a learnable, structurally bilateral weighting instead of a fixed subtraction. This design keeps both temporal branches explicit while remaining compact, and, together with a truncated backbone and grouped-query attention, LBTCap uses only 39.99M parameters, of which the change-aware encoder accounts for just 2.78M. Extensive experiments on two public RSICC datasets show that LBTCap matches or closely approaches the accuracy of state-of-the-art methods while using far fewer parameters and running at markedly higher inference speed, with the benefit of the bilateral formulation most pronounced in the low-resource setting, demonstrating a favorable accuracy-efficiency trade-off for practical RSICC.