# CROSS: Cascaded Distillation and Dual-Constraint Grounding for Remote Sensing Referring Segmentation

Source: [CROSS: Cascaded Distillation and Dual-Constraint Grounding for Remote Sensing Referring Segmentation](<https://www.sota2.com/research/paper/6a72c383bc6f0f0705846e75>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-08-07T05:00:01.339Z

Authors: Tingzhang Luo, Ruizhong Liu, Yichao Liu, Cheng Fan, Yu Liu, Jianyuan Guo

Published: 2026-08-04T05:24:05.000Z

## Abstract

Referring Remote Sensing Image Segmentation (RRSIS) has achieved significant progress through the integration of VLMs and the Segment Anything Model (SAM). However, this progress largely relies on strong pre-trained capabilities, while leaving two fundamental limitations insufficiently addressed: (1) Architectural Weak-Coupling, where the unidirectional flow forces reliance on coarse VLM prompts and wastes SAM's pixel-level structural guidance, causing localization drift; and (2) Object-Centric Semantic Bias, where models overemphasize dominant object semantics while remaining insensitive to spatial reasoning crucial for RRSIS. Motivated by these observations, we propose CROSS, a tightly integrated paradigm for RRSIS. First, we introduce Linguistic-Guided Cascaded Distillation (LGCD) to bridge the architectural gap, which distills SAM's geometric affinities as soft regularizers into VLM intermediate layers, injecting dense structural priors to refine localization. Second, Perspective-Spatial Contrastive Learning (PSCL) imposes cross-anchored constraints by mining mask-filtered deceptive distractors and spatial-linguistic counterfactuals as hard negatives, explicitly shattering semantic shortcuts to enforce genuine logical consistency. Extensive experiments on RRSIS benchmarks demonstrate that CROSS achieves state-of-the-art performance and maintains precise localization even under severe spatial description perturbations, standing as a robust new paradigm for RRSIS.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2608.03147>)

[PDF](<https://arxiv.org/pdf/2608.03147.pdf>)
