相关论文: Can Graphs Help Vision SSMs See Better?

Mamba, an architecture with RNN-like token mixer of state space model (SSM), was recently introduced to address the quadratic complexity of the attention mechanism and subsequently applied to vision tasks. Nevertheless, the performance of…

Mamba, with its advantages of global perception and linear complexity, has been widely applied to identify changes of the target regions within the remote sensing (RS) images captured under complex scenarios and varied conditions. However,…

Multimodal large language models are typically trained end-to-end to predict ground-truth answers, yet supervision signals are applied exclusively to text tokens. Visual tokens, the core carriers of visual information, are optimized only…

The convolution operation suffers from a limited receptive filed, while global modeling is fundamental to dense prediction tasks, such as semantic segmentation. In this paper, we apply graph convolution into the semantic segmentation task…

CNN- and Transformer-based architectures have achieved strong performance in medical image segmentation, but CNNs are limited in modeling long-range dependencies, while Transformers often suffer from quadratic computational and memory…

Existing Scene Text Recognition (STR) methods typically use a language model to optimize the joint probability of the 1D character sequence predicted by a visual recognition (VR) model, which ignore the 2D spatial context of visual…

Place recognition gives a SLAM system the ability to correct cumulative errors. Unlike images that contain rich texture features, point clouds are almost pure geometric information which makes place recognition based on point clouds…

Recent years have witnessed significant advancements in light field image super-resolution (LFSR) owing to the progress of modern neural networks. However, these methods often face challenges in capturing long-range dependencies (CNN-based)…

Deep state-space models (Deep SSMs) are becoming popular as effective approaches to model sequence data. They have also been shown to be capable of in-context learning, much like transformers. However, a complete picture of how SSMs might…

Learning structured task representations from human demonstrations is essential for understanding long-horizon manipulation behaviors, particularly in bimanual settings where action ordering, object involvement, and interaction geometry can…

Spatial Transcriptomics (ST) enables the measurement of gene expression while preserving spatial information, offering critical insights into tissue architecture and disease pathology. Recent developments have explored the use of…

Domain generalization~(DG) aims at solving distribution shift problems in various scenes. Existing approaches are based on Convolution Neural Networks (CNNs) or Vision Transformers (ViTs), which suffer from limited receptive fields or…

State-space models (SSMs) offer efficient alternatives to attention with linear-time recurrence. Mamba2, a recent SSM-based language model, uses selective input gating and a multi-head structure, enabling parallel computation and strong…

Probabilistic State Space Models (SSMs) are essential for Reinforcement Learning (RL) from high-dimensional, partial information as they provide concise representations for control. Yet, they lack the computational efficiency of their…

In recent years, Transformers have become the de-facto architecture for long-term sequence forecasting (LTSF), but faces challenges such as quadratic complexity and permutation invariant bias. A recent model, Mamba, based on selective state…

Similar to Vision Transformers, this paper identifies artifacts also present within the feature maps of Vision Mamba. These artifacts, corresponding to high-norm tokens emerging in low-information background areas of images, appear much…

Neuromorphic vision sensing (NVS)\ devices represent visual information as sequences of asynchronous discrete events (a.k.a., "spikes") in response to changes in scene reflectance. Unlike conventional active pixel sensing (APS), NVS allows…

Token interaction operation is one of the core modules in MLP-based models to exchange and aggregate information between different spatial locations. However, the power of token interaction on the spatial dimension is highly dependent on…

Transformer-based methods have achieved remarkable performance in event-based object detection, owing to the global modeling ability. However, they neglect the influence of non-event and noisy regions and process them uniformly, leading to…

Vascular segmentation in medical images is crucial for disease diagnosis and surgical navigation. However, the segmented vascular structure is often discontinuous due to its slender nature and inadequate prior modeling. In this paper, we…