相关论文: CalFuse: Multi-Modal Continual Learning via Featur…

The growth of Massive Open Online Courses (MOOCs) presents significant challenges for personalized learning, where concept recommendation is crucial. Existing approaches typically rely on heterogeneous information networks or knowledge…

Continual learning (CL) is a major challenge of machine learning (ML) and describes the ability to learn several tasks sequentially without catastrophic forgetting (CF). Recent works indicate that CL is a complex topic, even more so when…

Visual Question Answering (VQA) is a multi-discipline research task. To produce the right answer, it requires an understanding of the visual content of images, the natural language questions, as well as commonsense reasoning over the…

Reliable uncertainty estimation is critical for deploying neural networks (NNs) in real-world applications. While existing calibration techniques often rely on post-hoc adjustments or coarse-grained binning methods, they remain limited in…

Continual Learning (CL) enables machine learning models to learn from continuously shifting new training data in absence of data from old tasks. Recently, pretrained vision transformers combined with prompt tuning have shown promise for…

Large Language Models (LLMs) have achieved remarkable performance across various reasoning tasks, yet post-training is constrained by inefficient sample utilization and inflexible difficulty samples processing. To address these limitations,…

Large Multimodal Models (LMMs) are powerful tools that are capable of reasoning and understanding multimodal information beyond text and language. Despite their entrenched impact, the development of LMMs is hindered by the higher…

Integrating diverse data modalities is crucial for enhancing the performance of personalized recommendation systems. Traditional models, which often rely on singular data sources, lack the depth needed to accurately capture the multifaceted…

Person re-identification is an important task in video surveillance that aims to associate people across camera views at different locations and time. View variability is always a challenging problem seriously degrading person…

Dual-to-Dual MLLMs refer to Multimodal Large Language Models, which can enable unified multimodal comprehension and generation through text and image modalities. Although exhibiting strong instantaneous learning and generalization…

Federated learning (FL) has become a cornerstone in decentralized learning, where, in many scenarios, the incoming data distribution will change dynamically over time, introducing continuous learning (CL) problems. This continual federated…

Recent advances in deep learning underscore the need for systems that can not only acquire new knowledge through Continual Learning (CL) but also remove outdated, sensitive, or private information through Machine Unlearning (MU). However,…

Continual learning (CL) aims to learn new tasks without forgetting previous tasks. However, existing CL methods require a large amount of raw data, which is often unavailable due to copyright considerations and privacy risks. Instead,…

Federated Continual Learning (FCL) has emerged as a robust solution for collaborative model training in dynamic environments, where data samples are continuously generated and distributed across multiple devices. This survey provides a…

In deepfake detection, the varying degrees of compression employed by social media platforms pose significant challenges for model generalization and reliability. Although existing methods have progressed from single-modal to multimodal…

Incremental learning often encounter challenges such as overfitting to new data and catastrophic forgetting of old data. Existing methods can effectively extend the model for new tasks while freezing the parameters of the old model, but…

Machine unlearning (MU) has gained significant attention as a means to remove specific data from trained models without requiring a full retraining process. While progress has been made in unimodal domains like text and image…

Although multi-view unsupervised feature selection (MUFS) has demonstrated success in dimensionality reduction for unlabeled multi-view data, most existing methods reduce feature redundancy by focusing on linear correlations among features…

Federated Continual Learning (FCL) leverages inter-client collaboration to balance new knowledge acquisition and prior knowledge retention in non-stationary data. However, existing batch-based FCL methods lack adaptability to streaming…

Spatial scene understanding, including monocular depth estimation, is an important problem in various applications, such as robotics and autonomous driving. While improvements in unsupervised monocular depth estimation have potentially…