Related papers: MambaEye: A Size-Agnostic Visual Encoder with Caus…
Vision Mamba has emerged as a promising and efficient alternative to Vision Transformers, yet its efficiency remains fundamentally constrained by the number of input tokens. Existing token reduction approaches typically adopt token pruning…
The realm of Mamba for vision has been advanced in recent years to strike for the alternatives of Vision Transformers (ViTs) that suffer from the quadratic complexity. While the recurrent scanning mechanism of Mamba offers computational…
The Mamba-based image restoration backbones have recently demonstrated significant potential in balancing global reception and computational efficiency. However, the inherent causal modeling limitation of Mamba, where each token depends…
State Space Models (SSMs) with selective scan (Mamba) have been adapted into efficient vision models. Mamba, unlike Vision Transformers, achieves linear complexity for token interactions through a recurrent hidden state process. This…
Vision mambas have demonstrated strong performance with linear complexity to the number of vision tokens. Their efficiency results from processing image tokens sequentially. However, most existing methods employ patch-based image…
State-space models (SSMs), Mamba in particular, are increasingly adopted for long-context sequence modeling, providing linear-time aggregation via an input-dependent, causal selective-scan operation. Along this line, recent…
Mamba, a recent selective structured state space model, excels in long sequence modeling, which is vital in the large model era. Long sequence modeling poses significant challenges, including capturing long-range dependencies within the…
Recent State Space Models (SSM), especially Mamba, have demonstrated impressive performance in visual modeling and possess superior model efficiency. However, the application of Mamba to visual tasks suffers inferior performance due to…
Mamba has garnered widespread attention due to its flexible design and efficient hardware performance to process 1D sequences based on the state space model (SSM). Recent studies have attempted to apply Mamba to the visual domain by…
Perceptual image compression focuses on preserving high visual quality under low-bitrate constraints. Most existing approaches to perceptual compression leverage the strong generative capabilities of generative adversarial networks or…
State space models (SSMs) with selection mechanisms and hardware-aware architectures, namely Mamba, have recently demonstrated significant promise in long-sequence modeling. Since the self-attention mechanism in transformers has quadratic…
In the field of self-supervised depth estimation, Convolutional Neural Networks (CNNs) and Transformers have traditionally been dominant. However, both architectures struggle with efficiently handling long-range dependencies due to their…
Real-time cognitive load assessment from eye-tracking signals could potentially enable adaptive human-centered-AI such as safety-critical applications such as driver vigilance monitoring or automated flight deck assistance, yet two…
Linear modeling methods like Mamba have been merged as the effective backbone for the 3D object detection task. However, previous Mamba-based methods utilize the bidirectional encoding for the whole non-empty voxel sequence, which contains…
Video super-resolution (VSR) faces critical challenges in effectively modeling non-local dependencies across misaligned frames while preserving computational efficiency. Existing VSR methods typically rely on optical flow strategies or…
Recent advances in Vision Transformers (ViTs) and State Space Models (SSMs) have challenged the dominance of Convolutional Neural Networks (CNNs) in computer vision. ViTs excel at capturing global context, and SSMs like Mamba offer linear…
Recent advancements have highlighted the Mamba framework, a state-space model known for its efficiency in capturing long-range dependencies with linear computational complexity. While Mamba has shown competitive performance in medical image…
Recent advancements in State Space Models, notably Mamba, have demonstrated superior performance over the dominant Transformer models, particularly in reducing the computational complexity from quadratic to linear. Yet, difficulties in…
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…
We propose a novel hybrid Mamba-Transformer backbone, MambaVision, specifically tailored for vision applications. Our core contribution includes redesigning the Mamba formulation to enhance its capability for efficient modeling of visual…