Related papers: DepthMamba with Adaptive Fusion
Applying pre-trained models to assist point cloud understanding has recently become a mainstream paradigm in 3D perception. However, existing application strategies are straightforward, utilizing only the final output of the pre-trained…
Diffusion models have achieved great success in image generation, with the backbone evolving from U-Net to Vision Transformers. However, the computational cost of Transformers is quadratic to the number of tokens, leading to significant…
Restoration and enhancement are essential for improving the quality of videos captured under atmospheric turbulence conditions, aiding visualization, object detection, classification, and tracking in surveillance systems. In this paper, we…
Accurate survival prediction in oncology requires integrating diverse imaging modalities to capture the complex interplay of tumor biology. Traditional single-modality approaches often fail to leverage the complementary insights provided by…
Shadow removal aims to restore images that are partially degraded by shadows, where the degradation is spatially localized and non-uniform. Unlike general restoration tasks that assume global degradation, shadow removal can leverage…
In data-scarce scenarios, deep learning models often overfit to noise and irrelevant patterns, which limits their ability to generalize to unseen samples. To address these challenges in medical image segmentation, we introduce Diff-UMamba,…
Existing deraining Transformers employ self-attention mechanisms with fixed-range windows or along channel dimensions, limiting the exploitation of non-local receptive fields. In response to this issue, we introduce a novel dual-branch…
Unified Multimodal models (UMMs) built on a single architecture have shown impressive performance in both understanding and generation. We identify a fundamental challenge that lies in inductive biases induced by distinct supervision…
Infrared and visible image fusion aim to integrate modality strengths for visually enhanced, informative images. Visible imaging in real-world scenarios is susceptible to dynamic environmental brightness fluctuations, leading to texture…
Recent Mamba-based image restoration methods have achieved promising results but remain limited by fixed scanning patterns and inefficient feature utilization. Conventional Mamba architectures rely on predetermined paths that cannot adapt…
In the field of multi-source remote sensing image classification, remarkable progress has been made by using Convolutional Neural Network (CNN) and Transformer. Recently, Mamba-based methods built upon the State Space Model (SSM) have shown…
Detecting hidden or partially concealed objects remains a fundamental challenge in multimodal environments, where factors like occlusion, camouflage, and lighting variations significantly hinder performance. Traditional RGB-based detection…
3D human pose lifting is a promising research area that leverages estimated and ground-truth 2D human pose data for training. While existing approaches primarily aim to enhance the performance of estimated 2D poses, they often struggle when…
Self-supervised pretraining is promising for large-scale neuroimaging, yet the impact of region-aware masking and hybrid sequence modeling remains underexplored. In this work, we introduce Rhamba, a region-aware pretraining framework that…
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…
Recent advancements in the Mamba architecture, with its linear computational complexity, being a promising alternative to transformer architectures suffering from quadratic complexity. While existing works primarily focus on adapting Mamba…
Video anomaly detection (VAD) methods are mostly CNN-based or Transformer-based, achieving impressive results, but the focus on detection accuracy often comes at the expense of inference speed. The emergence of state space models in…
Handling lengthy context is crucial for enhancing the recognition and understanding capabilities of multimodal large language models (MLLMs) in applications such as processing high-resolution images or high frame rate videos. The rise in…
Motion planning is a challenging task to generate safe and feasible trajectories in highly dynamic and complex environments, forming a core capability for autonomous vehicles. In this paper, we propose DRAMA, the first Mamba-based…
This paper presents a framework for universal sound separation and polyphonic audio classification, addressing the challenges of separating and classifying individual sound sources in a multichannel mixture. The proposed framework,…