Related papers: DynaMMo: Dynamic Model Merging for Efficient Class…

Although deep learning approaches have stood out in recent years due to their state-of-the-art results, they continue to suffer from catastrophic forgetting, a dramatic decrease in overall performance when training with new classes added…

The challenge in LLM-based video understanding lies in preserving visual and semantic information in long videos while maintaining a memory-affordable token count. However, redundancy and correspondence in videos have hindered the…

In the recent past, complex deep neural networks have received huge interest in various document understanding tasks such as document image classification and document retrieval. As many document types have a distinct visual style, learning…

Federated Learning (FL) is a distributed machine learning (ML) paradigm, aiming to train a global model by exploiting the decentralized data across millions of edge devices. Compared with centralized learning, FL preserves the clients'…

Recently, MLP-like vision models have achieved promising performances on mainstream visual recognition tasks. In contrast with vision transformers and CNNs, the success of MLP-like models shows that simple information fusion operations…

Generative Diffusion Models (GDMs) have emerged as a transformative force in the realm of Generative Artificial Intelligence (GenAI), demonstrating their versatility and efficacy across various applications. The ability to model complex…

To achieve high performance of a machine learning (ML) task, a deep learning-based model must implicitly capture the entire distribution from data. Thus, it requires a huge amount of training samples, and data are expected to fully present…

Federated Learning (FL) is a decentralized approach for collaborative model training on edge devices. This distributed method of model training offers advantages in privacy, security, regulatory compliance, and cost-efficiency. Our emphasis…

Deep neural networks (DNNs) have demonstrated promising results in various complex tasks. However, current DNNs encounter challenges with over-parameterization, especially when there is limited training data available. To enhance the…

In recent years, deep learning has rapidly become a method of choice for the segmentation of medical images. Deep Neural Network (DNN) architectures such as UNet have achieved state-of-the-art results on many medical datasets. To further…

Multimodal image fusion aims to integrate information from different imaging techniques to produce a comprehensive, detail-rich single image for downstream vision tasks. Existing methods based on local convolutional neural networks (CNNs)…

Deep learning has proven to be a highly effective tool for a wide range of applications, significantly when leveraging the power of multi-loss functions to optimize performance on multiple criteria simultaneously. However, optimal selection…

Model merging has gained prominence in machine learning as a method to integrate multiple trained models into a single model without accessing the original training data. While existing approaches have demonstrated success in domains such…

Current multi-modal image fusion methods typically rely on task-specific models, leading to high training costs and limited scalability. While generative methods provide a unified modeling perspective, they often suffer from slow inference…

In this paper, we propose a novel data augmentation technique called GenMix, which combines generative and mixture approaches to leverage the strengths of both methods. While generative models excel at creating new data patterns, they face…

With the growing incorporation of deep neural network (DNN) models into modern software systems, the prohibitive construction costs have become a significant challenge. Model reuse has been widely applied to reduce training costs, but…

Federated learning (FL) systems face performance challenges in dealing with heterogeneous devices and non-identically distributed data across clients. We propose a dynamic global model aggregation method within Asynchronous Federated…

Distributed machine learning (DML) over time-varying networks can be an enabler for emerging decentralized ML applications such as autonomous driving and drone fleeting. However, the commonly used weighted arithmetic mean model aggregation…

Composed Image Retrieval (CIR) is a cross-modal task that aims to retrieve target images from large-scale databases using a reference image and a modification text. Most existing methods rely on a single model to perform feature fusion and…

Diffusion models have achieved remarkable success in generating high-quality images thanks to their novel training procedures applied to unprecedented amounts of data. However, training a diffusion model from scratch is computationally…