相关论文: DeMansia: Mamba Never Forgets Any Tokens

As one of the most representative DL techniques, Transformer architecture has empowered numerous advanced models, especially the large language models (LLMs) that comprise billions of parameters, becoming a cornerstone in deep learning.…

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…

Mamba, a special case of the State Space Model, is gaining popularity as an alternative to template-based deep learning approaches in medical image analysis. While transformers are powerful architectures, they have drawbacks, including…

Mamba is emerging as a novel approach to overcome the challenges faced by Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) in computer vision. While CNNs excel at extracting local features, they often struggle to capture…

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…

Recently, state space models (SSM), particularly Mamba, have attracted significant attention from scholars due to their ability to effectively balance computational efficiency and performance. However, most existing visual Mamba methods…

Transformers have become foundational for visual tasks such as object detection, semantic segmentation, and video understanding, but their quadratic complexity in attention mechanisms presents scalability challenges. To address these…

Mamba and Vision Mamba (Vim) models have shown their potential as an alternative to methods based on Transformer architecture. This work introduces Fast Mamba for Vision (Famba-V), a cross-layer token fusion technique to enhance the…

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…

State space models (SSMs), such as Mamba, have emerged as an efficient alternative to transformers for long-context sequence modeling. However, despite their growing adoption, SSMs lack the interpretability tools that have been crucial for…

State-of-the-art transformer-based large multimodal models (LMMs) struggle to handle hour-long video inputs due to the quadratic complexity of the causal self-attention operations, leading to high computational costs during training and…

Enhancing and preserving the readability of document images, particularly historical ones, is crucial for effective document image analysis. Numerous models have been proposed for this task, including convolutional-based, transformer-based,…

In recent years, Transformers have become the de-facto architecture for sequence modeling on text and a variety of multi-dimensional data, such as images and video. However, the use of self-attention layers in a Transformer incurs…

Deep learning has profoundly transformed remote sensing, yet prevailing architectures like Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) remain constrained by critical trade-offs: CNNs suffer from limited receptive…

Since the era of deep learning, convolutional neural networks (CNNs) and vision transformers (ViTs) have been extensively studied and widely used in medical image classification tasks. Unfortunately, CNN's limitations in modeling long-range…

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…

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…

Accurate and efficient multivariate time series (MTS) analysis is increasingly critical for a wide range of intelligent applications. Within this realm, Transformers have emerged as the predominant architecture due to their strong ability…

With the explosive growth of data, long-sequence modeling has become increasingly important in tasks such as natural language processing and bioinformatics. However, existing methods face inherent trade-offs between efficiency and memory.…

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…