Related papers: Dynamic Memory Transformer for Hyperspectral Image…

State-of-the-art ASR systems have achieved promising results by modeling local and global interactions separately. While the former can be computed efficiently, global interactions are usually modeled via attention mechanisms, which are…

Hyperspectral imaging (HSI) enables detailed land cover classification, yet low spatial resolution and sparse annotations pose significant challenges. We present a label-efficient framework that leverages spatial features from a frozen…

Medical image segmentation is a cornerstone of modern clinical diagnostics. While Vision Transformers that leverage shifted window-based self-attention have established new benchmarks in this field, they are often hampered by a critical…

Long-term weather forecasting is critical for socioeconomic planning and disaster preparedness. While recent approaches employ finetuning to extend prediction horizons, they remain constrained by the issues of catastrophic forgetting, error…

Due to the powerful ability in capturing the global information, Transformer has become an alternative architecture of CNNs for hyperspectral image classification. However, general Transformer mainly considers the global spectral…

Time series forecasting requires architectures that simultaneously achieve three competing objectives: (1) strict temporal causality for reliable predictions, (2) sub-quadratic complexity for practical scalability, and (3) multi-scale…

Hyperspectral Imaging (HSI) is known for its advantages over traditional RGB imaging in remote sensing, agriculture, and medicine. Recently, it has gained attention for enhancing Advanced Driving Assistance Systems (ADAS) perception.…

In hyperspectral remote sensing field, some downstream dense prediction tasks, such as semantic segmentation (SS) and change detection (CD), rely on supervised learning to improve model performance and require a large amount of manually…

B-mode ultrasound for breast cancer diagnosis faces challenges: speckle, operator dependency, and indistinct boundaries. Existing deep learning suffers from single-task learning, architectural constraints (CNNs lack global context,…

Transformers have revolutionized image modeling tasks with adaptations like DeIT, Swin, SVT, Biformer, STVit, and FDVIT. However, these models often face challenges with inductive bias and high quadratic complexity, making them less…

Semantic segmentation assigns labels to pixels in images, a critical yet challenging task in computer vision. Convolutional methods, although capturing local dependencies well, struggle with long-range relationships. Vision Transformers…

Learning the manifold structure of remote sensing images is of paramount relevance for modeling and understanding processes, as well as to encapsulate the high dimensionality in a reduced set of informative features for subsequent…

Spiking Neural Networks have attracted significant attention in recent years due to their distinctive low-power characteristics. Meanwhile, Transformer models, known for their powerful self-attention mechanisms and parallel processing…

Entropy estimation is essential for the performance of learned image compression. It has been demonstrated that a transformer-based entropy model is of critical importance for achieving a high compression ratio, however, at the expense of a…

Medical image segmentation faces challenges due to variations in anatomical structures. While convolutional neural networks (CNNs) effectively capture local features, they struggle with modeling long-range dependencies. Transformers…

Current semantic segmentation models have achieved great success under the independent and identically distributed (i.i.d.) condition. However, in real-world applications, test data might come from a different domain than training data.…

In recent years, deep learning (DL) models have shown outstanding performance in EEG classification tasks, particularly in Steady-State Visually Evoked Potential(SSVEP)-based Brain-Computer-Interfaces(BCI)systems. DL methods have been…

Accurate classification of hyperspectral imagery (HSI) is often frustrated by the tension between high-dimensional spectral data and the extreme scarcity of labeled training samples. While hierarchical models like LoLA-SpecViT have…

Class-incremental/Continual image segmentation (CIS) aims to train an image segmenter in stages, where the set of available categories differs at each stage. To leverage the built-in objectness of query-based transformers, which mitigates…

The computer vision community has witnessed an extensive exploration of vision transformers in the past two years. Drawing inspiration from traditional schemes, numerous works focus on introducing vision-specific inductive biases. However,…