相关论文: MambaMIL: Enhancing Long Sequence Modeling with Se…

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.…

Multiple Instance Learning (MIL) is a weakly-supervised problem in which one label is assigned to the whole bag of instances. An important class of MIL models is instance-based, where we first classify instances and then aggregate those…

Multiple instance learning (MIL) significantly reduced annotation costs via bag-level weak labels for large-scale images, such as histopathological whole slide images (WSIs). However, its adaptability to continual tasks with minimal…

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…

Recent sequence modeling approaches using selective state space sequence models, referred to as Mamba models, have seen a surge of interest. These models allow efficient processing of long sequences in linear time and are rapidly being…

Recurrent neural networks and Transformers have recently dominated most applications in hyperspectral (HS) imaging, owing to their capability to capture long-range dependencies from spectrum sequences. However, despite the success of these…

Mamba, a recently proposed linear-time sequence model, has attracted significant attention for its computational efficiency and strong empirical performance. However, a rigorous theoretical understanding of its underlying mechanisms remains…

Single image super-resolution (SR) has long posed a challenge in the field of computer vision. While the advent of deep learning has led to the emergence of numerous methods aimed at tackling this persistent issue, the current methodologies…

Sequence modeling is a crucial area across various domains, including Natural Language Processing (NLP), speech recognition, time series forecasting, music generation, and bioinformatics. Recurrent Neural Networks (RNNs) and Long Short Term…

Multiple Instance Learning (MIL) is a cornerstone approach in computational pathology (CPath) for generating clinically meaningful slide-level embeddings from gigapixel tissue images. However, MIL often struggles with small, weakly…

In computational pathology, weak supervision has become the standard for deep learning due to the gigapixel scale of WSIs and the scarcity of pixel-level annotations, with Multiple Instance Learning (MIL) established as the principal…

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…

Multiple instance learning (MIL) has been increasingly used in the classification of histopathology whole slide images (WSIs). However, MIL approaches for this specific classification problem still face unique challenges, particularly those…

Sequential modeling has demonstrated remarkable capabilities in offline reinforcement learning (RL), with Decision Transformer (DT) being one of the most notable representatives, achieving significant success. However, RL trajectories…

Spatial-Spectral Mamba (SSM) improves computational efficiency and captures long-range dependencies, addressing Transformer limitations. However, traditional Mamba models overlook rich spectral information in HSIs and struggle with high…

Algorithm Distillation (AD) was recently proposed as a new approach to perform In-Context Reinforcement Learning (ICRL) by modeling across-episodic training histories autoregressively with a causal transformer model. However, due to…

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…

Sequential recommendation systems have become a cornerstone of personalized services, adept at modeling the temporal evolution of user preferences by capturing dynamic interaction sequences. Existing approaches predominantly rely on…

Radiography imaging protocols target on specific anatomical regions, resulting in highly consistent images with recurrent structural patterns across patients. Recent advances in medical anomaly detection have demonstrated the effectiveness…

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…