Related papers: DUKAE: DUal-level Knowledge Accumulation and Ensem…
Continual learning aims to allow models to learn new tasks without forgetting what has been learned before. This work introduces Elastic Variational Continual Learning with Weight Consolidation (EVCL), a novel hybrid model that integrates…
The deployment of pre-trained models (PTMs) has greatly advanced the field of continual learning (CL), enabling positive knowledge transfer and resilience to catastrophic forgetting. To sustain these advantages for sequentially arriving…
Class-incremental learning is dedicated to the development of deep learning models that are capable of acquiring new knowledge while retaining previously learned information. Most methods focus on balanced data distribution for each task,…
We introduce Constr-DRKM, a deep kernel method for the unsupervised learning of disentangled data representations. We propose augmenting the original deep restricted kernel machine formulation for kernel PCA by orthogonality constraints on…
The Mixture-of-Experts (MoE) model has succeeded in deep learning (DL). However, its complex architecture and advantages over dense models in image classification remain unclear. In previous studies, MoE performance has often been affected…
Federated Learning (FL) has revolutionized how we train deep neural networks by enabling decentralized collaboration while safeguarding sensitive data and improving model performance. However, FL faces two crucial challenges: the diverse…
Mixture of Experts (MoE) architectures have recently advanced the scalability and adaptability of large language models (LLMs) for continual multimodal learning. However, efficiently extending these models to accommodate sequential tasks…
Deep learning models suffer from catastrophic forgetting of the classes in the older phases as they get trained on the classes introduced in the new phase in the class-incremental learning setting. In this work, we show that the effect of…
We propose a new method for unsupervised generative continual learning through realignment of Variational Autoencoder's latent space. Deep generative models suffer from catastrophic forgetting in the same way as other neural structures.…
Recent advancements in data-driven task-oriented dialogue systems (ToDs) struggle with incremental learning due to computational constraints and time-consuming issues. Continual Learning (CL) attempts to solve this by avoiding intensive…
Recently, multi-modality scene perception tasks, e.g., image fusion and scene understanding, have attracted widespread attention for intelligent vision systems. However, early efforts always consider boosting a single task unilaterally and…
Deep neural networks, despite their remarkable success, remain fundamentally limited in their ability to perform Continual Learning (CL). While most current methods aim to enhance the capabilities of a single model, Inspired by the…
With the increasing of model capacity brought by pre-trained language models, there emerges boosting needs for more knowledgeable natural language processing (NLP) models with advanced functionalities including providing and making flexible…
Accurate brain tumor classification is crucial in medical imaging to ensure reliable diagnosis and effective treatment planning. This study introduces a novel double ensembling framework that synergistically combines pre-trained deep…
Adapting general large language models (LLMs) to specialized domains presents great challenges due to varied data distributions. This adaptation typically requires continual pre-training on massive domain-specific corpora to facilitate…
Standard deep neural networks (DNNs) are commonly trained in an end-to-end fashion for specific tasks such as object recognition, face identification, or character recognition, among many examples. This specificity often leads to…
Image classification is a fundamental computer vision task and an important baseline for deep metric learning. In decades efforts have been made on enhancing image classification accuracy by using deep learning models while less attention…
With the rapid development of deep learning, there have been an unprecedentedly large number of trained deep network models available online. Reusing such trained models can significantly reduce the cost of training the new models from…
Multimodal large language models (MLLMs) have garnered widespread attention from researchers due to their remarkable understanding and generation capabilities in visual language tasks (e.g., visual question answering). However, the rapid…
The intrinsic capability to continuously learn a changing data stream is a desideratum of deep neural networks (DNNs). However, current DNNs suffer from catastrophic forgetting, which interferes with remembering past knowledge. To mitigate…