Related papers: RoMA: Scaling up Mamba-based Foundation Models for…

Hyperspectral image (HSI) classification is pivotal in the remote sensing (RS) field, particularly with the advancement of deep learning techniques. Sequential models, adapted from the natural language processing (NLP) field such as…

State Space Models (SSMs), particularly the Mamba architecture, have recently emerged as powerful alternatives to Transformers for sequence modeling, offering linear computational complexity while achieving competitive performance. Yet,…

Foundation models learn transferable representations, motivating growing interest in their application to wireless systems. Existing wireless foundation models are predominantly based on transformer architectures, whose quadratic…

Task failures in prior fine-grained robotic manipulation methods often stem from suboptimal initial grasping, which is critical for subsequent manipulation and reducing the requirement for complex pose adjustments. To address this, we…

Mamba-based architectures have shown to be a promising new direction for deep learning models owing to their competitive performance and sub-quadratic deployment speed. However, current Mamba multi-modal large language models (MLLM) are…

Multicategory remote object counting is a fundamental task in computer vision, aimed at accurately estimating the number of objects of various categories in remote images. Existing methods rely on CNNs and Transformers, but CNNs struggle to…

Recent advancements in state space models, notably Mamba, have demonstrated significant progress in modeling long sequences for tasks like language understanding. Yet, their application in vision tasks has not markedly surpassed the…

Accurate building segmentation and height estimation from single-view RGB satellite imagery are fundamental for urban analytics, yet remain ill-posed due to structural variability and the high computational cost of global context modeling.…

Recent efforts on image restoration have focused on developing "all-in-one" models that can handle different degradation types and levels within single model. However, most of mainstream Transformer-based ones confronted with dilemma…

Multi-source remote sensing enables complementary observation of ground objects, while cross-modal fine-grained object retrieval remains challenging, especially under unaligned optical and SAR conditions. Unlike conventional retrieval…

High-resolution remotely sensed images pose a challenge for commonly used semantic segmentation methods such as Convolutional Neural Network (CNN) and Vision Transformer (ViT). CNN-based methods struggle with handling such high-resolution…

Semantic segmentation is a vital task in the field of remote sensing (RS). However, conventional convolutional neural network (CNN) and transformer-based models face limitations in capturing long-range dependencies or are often…

Snapshot Compressive Imaging (SCI) enables fast spectral imaging but requires effective decoding algorithms for hyperspectral image (HSI) reconstruction from compressed measurements. Current CNN-based methods are limited in modeling…

Despite their frequent use for change detection, both ConvNets and Vision transformers (ViT) exhibit well-known limitations, namely the former struggle to model long-range dependencies while the latter are computationally inefficient,…

Grasp detection is a fundamental robotic task critical to the success of many industrial applications. However, current language-driven models for this task often struggle with cluttered images, lengthy textual descriptions, or slow…

U-shaped architectures have long dominated the field of medical image segmentation, while Transformers are widely employed for modeling long-range dependencies. The former typically handles scale variations implicitly by aggregating…

Remote sensing (RS) techniques are increasingly crucial for deepening our understanding of the planet. As the volume and diversity of RS data continue to grow exponentially, there is an urgent need for advanced data modeling and…

Recent advances in deep learning for vision tasks have seen the rise of State Space Models (SSMs) like Mamba, celebrated for their linear scalability. However, their adaptation to 2D visual data often necessitates complex modifications that…

Transformer-based architectures have become the backbone of both uni-modal and multi-modal foundation models, largely due to their scalability via attention mechanisms, resulting in a rich ecosystem of publicly available pre-trained models…

Place recognition is the foundation for enabling autonomous systems to achieve independent decision-making and safe operations. It is also crucial in tasks such as loop closure detection and global localization within SLAM. Previous methods…