Related papers: Dual-Kernel Adapter: Expanding Spatial Horizons fo…

Pansharpening is a challenging image fusion task that involves restoring images using two different modalities: low-resolution multispectral images (LRMS) and high-resolution panchromatic (PAN). Many end-to-end specialized models based on…

Transformer-based models have been widely demonstrated to be successful in computer vision tasks by modelling long-range dependencies and capturing global representations. However, they are often dominated by features of large patterns…

Deep learning has revolutionized the performance of classification, but meanwhile demands sufficient labeled data for training. Given insufficient data, while many techniques have been developed to help combat overfitting, the challenge…

Dimensionality reduction represents a critical preprocessing step in order to increase the efficiency and the performance of many hyperspectral imaging algorithms. However, dimensionality reduction algorithms, such as the Principal…

Fine-tuning large foundation models is essential for building expert models tailored to specialized tasks and domains, but fully updating billions of parameters is computationally prohibitive. Reducing the number of trainable parameters…

This paper proposes a novel approach to address the challenge that pretrained VLA models often fail to effectively improve performance and reduce adaptation costs during standard supervised finetuning (SFT). Some advanced finetuning methods…

An efficient computational approach for optimal reconstructing parameters of binary-type physical properties for models in biomedical applications is developed and validated. The methodology includes gradient-based multiscale optimization…

Vision transformers have recently set off a new wave in the field of medical image analysis due to their remarkable performance on various computer vision tasks. However, recent hybrid-/transformer-based approaches mainly focus on the…

While modern text-to-image models excel at prompt-based generation, they often lack the fine-grained control necessary for specific user requirements like spatial layouts or subject appearances. Multi-condition control addresses this, yet…

Accurate medical image segmentation plays a crucial role in overall diagnosis and is one of the most essential tasks in the diagnostic pipeline. CNN-based models, despite their extensive use, suffer from a local receptive field and fail to…

Convolutional neural networks (CNNs) have been not only widespread but also achieved noticeable results on numerous applications including image classification, restoration, and generation. Although the weight-sharing property of…

With the widespread deployment of deep learning models, they influence their environment in various ways. The induced distribution shifts can lead to unexpected performance degradation in deployed models. Existing methods to anticipate…

Attention mechanisms have significantly advanced visual models by capturing global context effectively. However, their reliance on large-scale datasets and substantial computational resources poses challenges in data-scarce and…

Medical image segmentation using deep neural networks has been highly successful. However, the effectiveness of these networks is often limited by inadequate dense prediction and inability to extract robust features. To achieve refined…

Meta-learning facilitates few-shot hyperspectral target detection (HTD), but adapting deep backbones remains challenging. Full-parameter fine-tuning is inefficient and prone to overfitting, and existing methods largely ignore the…

Accurate 3D medical image segmentation is vital for diagnosis and treatment planning, but state-of-the-art models are often too large for clinics with limited computing resources. Lightweight architectures typically suffer significant…

The scarcity of annotated data, particularly for rare diseases, limits the variability of training data and the range of detectable lesions, presenting a significant challenge for supervised anomaly detection in medical imaging. To solve…

Modern multi-access 5G+ networks provide mobile terminals with additional capacity, improving network stability and performance. However, in highly mobile environments such as vehicular networks, supporting multi-access connectivity remains…

Many software systems today face uncertain operating conditions, such as sudden changes in the availability of resources or unexpected user behavior. Without proper mitigation these uncertainties can jeopardize the system goals.…

Convolutional neural networks (CNNs) have achieved exciting performance in joint segmentation of optic disc and optic cup on single-institution datasets. However, their clinical translation is hindered by two major challenges: limited…