Related papers: Spectral State Space Model for Rotation-Invariant …
Transformers dominate NLP and IR; but their inference inefficiencies and challenges in extrapolating to longer contexts have sparked interest in alternative model architectures. Among these, state space models (SSMs) like Mamba offer…
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…
State Space Models (SSMs) have emerged as a promising alternative to the popular transformer-based models and have been increasingly gaining attention. Compared to transformers, SSMs excel at tasks with sequential data or longer contexts,…
Image restoration is a key task in low-level computer vision that aims to reconstruct high-quality images from degraded inputs. The emergence of Vision Mamba, which draws inspiration from the advanced state space model Mamba, marks a…
The Mamba layer offers an efficient selective state space model (SSM) that is highly effective in modeling multiple domains, including NLP, long-range sequence processing, and computer vision. Selective SSMs are viewed as dual models, in…
Mainstream approaches to spectral reconstruction (SR) primarily focus on designing Convolution- and Transformer-based architectures. However, CNN methods often face challenges in handling long-range dependencies, whereas Transformers are…
The goal of style transfer is, given a content image and a style source, generating a new image preserving the content but with the artistic representation of the style source. Most of the state-of-the-art architectures use transformers or…
For the deployment of neural networks in resource-constrained environments, prior works have built lightweight architectures with convolution and attention for capturing local and global dependencies, respectively. Recently, the state space…
As remote sensing imaging technology continues to advance and evolve, processing high-resolution and diversified satellite imagery to improve segmentation accuracy and enhance interpretation efficiency emerg as a pivotal area of…
Vision transformers dominate image processing tasks due to their superior performance. However, the quadratic complexity of self-attention limits the scalability of these systems and their deployment on resource-constrained devices. State…
State Space Models (SSMs) like Mamba2 are a promising alternative to Transformers, with faster theoretical training and inference times -- especially for long context lengths. Recent work on Matryoshka Representation Learning -- and its…
Accurate 3D medical image segmentation demands architectures capable of reconciling global context modeling with spatial topology preservation. While State Space Models (SSMs) like Mamba show potential for sequence modeling, existing…
In this paper, we analyze the computational limitations of Mamba and State-space Models (SSMs) by using the circuit complexity framework. Despite Mamba's stateful design and recent attention as a strong candidate to outperform Transformers,…
State Space Models (SSMs), particularly recent selective variants like Mamba, have emerged as a leading architecture for sequence modeling, challenging the dominance of Transformers. However, the success of these state-of-the-art models…
The evolution of diffusion models has greatly impacted video generation and understanding. Particularly, text-to-video diffusion models (VDMs) have significantly facilitated the customization of input video with target appearance, motion,…
As one of the tasks in Image Fusion, Infrared and Visible Image Fusion aims to integrate complementary information captured by sensors of different modalities into a single image. The Selective State Space Model (SSSM), known for its…
Standard representation probing for visual models relies on mathematically permutation-invariant operations like Global Average Pooling (GAP) or CLS tokens, treating patch representations as an unstructured bag-of-words. We challenge this…
Achieving both high accuracy and topological continuity in road segmentation from satellite imagery is a critical goal for applications ranging from urban planning to disaster response. State-of-the-art methods often rely on Vision…
State-space models (SSMs) are a highly expressive model class for learning patterns in time series data and for system identification. Deterministic versions of SSMs (e.g. LSTMs) proved extremely successful in modeling complex time series…
Arbitrary scale super-resolution (ASSR) aims to super-resolve low-resolution images to high-resolution images at any scale using a single model, addressing the limitations of traditional super-resolution methods that are restricted to…