Remote sensing images are increasingly used in applications, such as environmental monitoring and urban planning. However, the complexity of these images poses challenges for accurate object segmentation, particularly when guided by referring expressions. In this letter, we propose RSTG-segment anything model (SAM), a novel two-stage framework for referring remote sensing image segmentation (RRSIS), which builds upon the SAM. In the first stage, a multimodal encoder and a transformer-based prompt generator produce a sparse prompt that provides coarse object localization based on fused vision-language features. In the second stage, SAM utilizes this prompt to conduct fine-grained segmentation. We also introduce a lightweight text-guided adapter module for the efficient fine-tuning of SAM and a dual-attention fusion (DAF) module to enhance multimodal alignment. Experiments on the RRSIS-D dataset demonstrate that RSTG-SAM achieves the state-of-the-art performance across multiple metrics, particularly in handling small targets.

The Few-Shot Segmentation (FSS) aims to accomplish the novel class segmentation task with a few annotated images. Current FSS research based on meta-learning focuses on designing a complex interaction mechanism between the query and support feature. However, unlike humans who can rapidly learn new things from limited samples, the existing approach relies solely on fixed feature matching to tackle new tasks, lacking adaptability. In this paper, we propose a novel framework based on the adapter mechanism, namely Adaptive FSS, which can efficiently adapt the existing FSS model to the novel classes. In detail, we design the Prototype Adaptive Module (PAM), which utilizes accurate category information provided by the support set to derive class prototypes, enhancing class-specific information in the multi-stage representation. In addition, our approach is compatible with diverse FSS methods with different backbones by simply inserting PAM between the layers of the encoder. Experiments demonstrate that our method effectively improves the performance of the FSS models (e.g., MSANet, HDMNet, FPTrans, and DCAMA) and achieves new state-of-the-art (SOTA) results (i.e., 72.4% and 79.1% mIoU on PASCAL-5i 1-shot and 5-shot settings, 52.7% and 60.0% mIoU on COCO-20i 1-shot and 5-shot settings). Our code is available at https://github.com/jingw193/AdaptiveFSS.

Referring expression segmentation (RES) aims at segmenting the foreground masks of the entities that match the descriptive natural language expression. Previous datasets and methods for classic RES task heavily rely on the prior assumption that one expression must refer to object-level targets. In this paper, we take a step further to finer-grained part-level RES task. To promote the object-level RES task towards finer-grained vision-language understanding, we put forward a new multi-granularity referring expression segmentation (MRES) task and construct an evaluation benchmark called RefCOCOm by manual annotations. By employing our automatic model-assisted data engine, we build the largest visual grounding dataset namely MRES-32M, which comprises over 32.2M high-quality masks and captions on the provided 1M images. Besides, a simple yet strong model named UniRES is designed to accomplish the unified object-level and part-level grounding task. Extensive experiments on our RefCOCOm for MRES and three datasets (i.e., RefCOCO(+/g)) for classic RES task demonstrate the superiority of our method over previous state-of-the-art methods. To foster future research into fine-grained visual grounding, our benchmark RefCOCOm, the MRES-32M dataset and model UniRES will be publicly available at https://github.com/Rubics-Xuan/MRES.

Referring image segmentation (RIS) is a fundamental vision-language task that intends to segment a desired object from an image based on a given natural language expression. Due to the essentially distinct data properties between image and text, most of existing methods either introduce complex designs towards fine-grained vision-language alignment or lack required dense alignment, resulting in scalability issues or mis-segmentation problems such as over- or under-segmentation. To achieve effective and efficient fine-grained feature alignment in the RIS task, we explore the potential of masked multimodal modeling coupled with self-distillation and propose a novel cross-modality masked self-distillation framework named CM-MaskSD, in which our method inherits the transferred knowledge of image-text semantic alignment from CLIP model to realize fine-grained patch-word feature alignment for better segmentation accuracy. Moreover, our CM-MaskSD framework can considerably boost model performance in a nearly parameter-free manner, since it shares weights between the main segmentation branch and the introduced masked self-distillation branches, and solely introduces negligible parameters for coordinating the multimodal features. Comprehensive experiments on three benchmark datasets (ie RefCOCO, RefCOCO+, G-Ref) for the RIS task convincingly demonstrate the superiority of our proposed framework over previous state-of-the-art methods.