# Scale-wise Bidirectional Alignment Network for Referring Remote Sensing Image Segmentation

arXiv: https://arxiv.org/abs/2501.00851 · HTML: https://mlsanity.com/paper/2501.00851/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 12 references that are in the map.
- First posted on arXiv 1 Jan 2025.

## Builds on (most cited first, 8 of 8)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://mlsanity.com/paper/2107.06278/) (2021)
- [RemoteCLIP: A Vision Language Foundation Model for Remote Sensing](https://mlsanity.com/paper/2306.11029/) (2023)
- [Cross-Modal Progressive Comprehension for Referring Segmentation](https://mlsanity.com/paper/2105.07175/) (2021)
- [RRSIS: Referring Remote Sensing Image Segmentation](https://mlsanity.com/paper/2306.08625/) (2023)
- [Cross-aware Early Fusion with Stage-divided Vision and Language Transformer Encoders for Referring Image Segmentation](https://mlsanity.com/paper/2408.07539/) (2024)
- [CM-MaskSD: Cross-Modality Masked Self-Distillation for Referring Image Segmentation](https://mlsanity.com/paper/2305.11481/) (2023)

## Built on by (most cited first, 11 of 11)

- [RSRefSeg 2: Decoupling Referring Remote Sensing Image Segmentation with Foundation Models](https://mlsanity.com/paper/2507.06231/) (2025)
- [AeroReformer: Aerial Referring Transformer for UAV-based Referring Image Segmentation](https://mlsanity.com/paper/2502.16680/) (2025)
- [CroBIM-U: Uncertainty-Driven Referring Remote Sensing Image Segmentation](https://mlsanity.com/paper/2601.03490/) (2026)
- [Generalized Referring Expression Segmentation on Aerial Photos](https://mlsanity.com/paper/2512.07338/) (2025)
- [Enabling Training-Free Text-Based Remote Sensing Segmentation](https://mlsanity.com/paper/2602.17799/) (2026)
- [CROSS: Cascaded Distillation and Dual-Constraint Grounding for Remote Sensing Referring Segmentation](https://mlsanity.com/paper/2608.03147/) (2026)
- [Breaking the Box: Enhancing Remote Sensing Image Segmentation with Freehand Sketches](https://mlsanity.com/paper/2503.12191/) (2025)
- [Semantic-Driven Scale and Spatial Selection for Efficient Cross-Modal Alignment in Referring Remote Sensing Image Segmentation](https://mlsanity.com/paper/2606.30244/) (2026)
- [AeroReformer2: Spoken-Query Referring Segmentation for Aerial Images](https://mlsanity.com/paper/2608.08874/) (2026)
- [DiCoR: Decoupled Referent Disambiguation and Contour Recalibration for Efficient Referring Remote Sensing Image Segmentation](https://mlsanity.com/paper/2608.12980/) (2026)
- [Shift-Aware Identity-Guided Latent Refinement for Referring Audio--Visual Segmentation](https://mlsanity.com/paper/2610.12783/) (2026)

## Abstract (arXiv)

The goal of referring remote sensing image segmentation (RRSIS) is to extract specific pixel-level regions within an aerial image via a natural language expression. Recent advancements, particularly Transformer-based fusion designs, have demonstrated remarkable progress in this domain. However, existing methods primarily focus on refining visual features using language-aware guidance during the cross-modal fusion stage, neglecting the complementary vision-to-language flow. This limitation often leads to irrelevant or suboptimal representations. In addition, the diverse spatial scales of ground objects in aerial images pose significant challenges to the visual perception capabilities of existing models when conditioned on textual inputs. In this paper, we propose an innovative framework called Scale-wise Bidirectional Alignment Network (SBANet) to address these challenges for RRSIS. Specifically, we design a Bidirectional Alignment Module (BAM) with learnable query tokens to selectively and effectively represent visual and linguistic features, emphasizing regions associated with key tokens. BAM is further enhanced with a dynamic feature selection block, designed to provide both macro- and micro-level visual features, preserving global context and local details to facilitate more effective cross-modal interaction. Furthermore, SBANet incorporates a text-conditioned channel and spatial aggregator to bridge the gap between the encoder and decoder, enhancing cross-scale information exchange in complex aerial scenarios. Extensive experiments demonstrate that our proposed method achieves superior performance in comparison to previous state-of-the-art methods on the RRSIS-D and RefSegRS datasets, both quantitatively and qualitatively. The code will be released after publication.