Related papers: RSRefSeg 2: Decoupling Referring Remote Sensing Im…
Semantic segmentation (SS) of RSIs enables the fine-grained interpretation of surface features, making it a critical task in RS analysis. With the increasing diversity and volume of RSIs collected by sensors on various platforms,…
Single Image Reflection Separation (SIRS) disentangles mixed images into transmission and reflection layers. Existing methods suffer from transmission-reflection confusion under nonlinear mixing, particularly in deep decoder layers, due to…
Interactive segmentation models such as the Segment Anything Model (SAM) have demonstrated remarkable generalization on natural images, but they perform suboptimally on remote sensing imagery (RSI) due to severe domain shifts and the…
Referring remote sensing image segmentation (RRSIS) is a novel visual task in remote sensing images segmentation, which aims to segment objects based on a given text description, with great significance in practical application. Previous…
The reasoning segmentation task involves segmenting objects within an image by interpreting implicit user instructions, which may encompass subtleties such as contextual cues and open-world knowledge. Despite significant advancements made…
Remote sensing change understanding (RSCU) is essential for analyzing remote sensing images and understanding how human activities affect the environment. However, existing datasets lack deep understanding and interactions in the diverse…
Remote sensing has become critical for understanding environmental dynamics, urban planning, and disaster management. However, traditional remote sensing workflows often rely on explicit segmentation or detection methods, which struggle to…
Large-scale vision-language models like CLIP have demonstrated impressive open-vocabulary capabilities for image-level tasks, excelling in recognizing what objects are present. However, they struggle with pixel-level recognition tasks like…
Reasoning segmentation is an emerging vision-language task that requires reasoning over intricate text queries to precisely segment objects. However, existing methods typically suffer from overthinking, generating verbose reasoning chains…
Referring Image Segmentation (RIS) aims to segment an object described in natural language from an image, with the main challenge being a text-to-pixel correlation. Previous methods typically rely on single-modality features, such as vision…
The complexity of scenes and variations in image quality result in significant variability in the performance of semantic segmentation methods of remote sensing imagery (RSI) in supervised real-world scenarios. This makes the evaluation of…
Remote sensing image change captioning (RSICC) aims to achieve high-level semantic understanding of genuine changes occurring between bi-temporal images. Despite notable progress, existing methods are fundamentally limited by a shared…
In this work, we address the task of referring image segmentation (RIS), which aims at predicting a segmentation mask for the object described by a natural language expression. Most existing methods focus on establishing unidirectional or…
Remote sensing image captioning has advanced rapidly through encoder--decoder models, although the reliance on large annotated datasets and the focus on English restricts global applicability. To address these limitations, we propose the…
Remote sensing change captioning (RSICC) aims to describe changes between bitemporal images in natural language. Existing methods often fail under challenges like illumination differences, viewpoint changes, blur effects, leading to…
Medical image segmentation is more clinically valuable when it supports diagnosis rather than merely producing lesion masks. However, diagnostically relevant lesion cues are often subtle and localized, while existing models may be…
Referring Expression Segmentation (RES) is a core vision-language segmentation task that enables pixel-level understanding of targets via free-form linguistic expressions, supporting critical applications such as human-robot interaction and…
Recent segmentation methods, which adopt large-scale data training and transformer architecture, aim to create one foundation model that can perform multiple tasks. However, most of these methods rely on heavy encoder and decoder…
Referring image segmentation (RIS) requires dense vision-language interactions between visual pixels and textual words to segment objects based on a given description. However, commonly adapted dual-encoders in RIS, e.g., Swin transformer…
Referring image segmentation aims to produce a pixel-level mask for the image region described by a natural-language expression. Although pretrained vision-language models have improved semantic grounding, many existing methods still rely…