Related papers: Cut out and Replay: A Simple yet Versatile Strateg…

Online deep learning tackles the challenge of learning from data streams by balancing two competing goals: fast learning and deep learning. However, existing research primarily emphasizes deep learning solutions, which are more adept at…

Online Continual learning is a challenging learning scenario where the model must learn from a non-stationary stream of data where each sample is seen only once. The main challenge is to incrementally learn while avoiding catastrophic…

Continual learning aims to learn multiple tasks sequentially. A key challenge in continual learning is balancing between two objectives: retaining knowledge from old tasks (stability) and adapting to new tasks (plasticity). Experience…

Online Continual Learning (OCL) empowers machine learning models to acquire new knowledge online across a sequence of tasks. However, OCL faces a significant challenge: catastrophic forgetting, wherein the model learned in previous tasks is…

Semantic overlap among land-cover categories, highly imbalanced label distributions, and complex inter-class co-occurrence patterns constitute significant challenges for multi-label remote-sensing image retrieval. In this article,…

Foundational Vision-Language Models (VLMs) excel across diverse tasks, but adapting them to new domains without forgetting prior knowledge remains a critical challenge. Continual Learning (CL) addresses this challenge by enabling models to…

Even in the era of large models, one of the well-known issues in continual learning (CL) is catastrophic forgetting, which is significantly challenging when the continual data stream exhibits a long-tailed distribution, termed as…

Multimodal Contrastive Learning (MCL) advances in aligning different modalities and generating multimodal representations in a joint space. By leveraging contrastive learning across diverse modalities, large-scale multimodal data enhances…

Continual learning aims to learn continuously from a stream of tasks and data in an online-learning fashion, being capable of exploiting what was learned previously to improve current and future tasks while still being able to perform well…

Algorithm selection is commonly used to predict the best solver from a portfolio per per-instance. In many real scenarios, instances arrive in a stream: new instances become available over time, while the number of class labels can also…

Partially-supervised learning can be challenging for segmentation due to the lack of supervision for unlabeled structures, and the methods directly applying fully-supervised learning could lead to incompatibility, meaning ground truth is…

Traditional Incremental Learning (IL) targets to handle sequential fully-supervised learning problems where novel classes emerge from time to time. However, due to inherent annotation uncertainty and ambiguity, collecting high-quality…

The development of accurate methods for multi-label classification (MLC) of remote sensing (RS) images is one of the most important research topics in RS. The MLC methods based on convolutional neural networks (CNNs) have shown strong…

In-context learning (ICL) is an emerging capability of large autoregressive language models where a few input-label demonstrations are appended to the input to enhance the model's understanding of downstream NLP tasks, without directly…

Open-world continual learning (OWCL) adapts to sequential tasks with open samples, learning knowledge incrementally while preventing forgetting. However, existing OWCL still requires a large amount of labeled data for training, which is…

Continual learning enables AI systems to acquire new knowledge while retaining previously learned information. While traditional unimodal methods have made progress, the rise of Multimodal Large Language Models (MLLMs) brings new challenges…

The goal of multi-label learning (MLL) is to associate a given instance with its relevant labels from a set of concepts. Previous works of MLL mainly focused on the setting where the concept set is assumed to be fixed, while many real-world…

Joint clustering and feature learning methods have shown remarkable performance in unsupervised representation learning. However, the training schedule alternating between feature clustering and network parameters update leads to unstable…

Multi-label classification (MLC) faces challenges from label noise in training data due to annotating diverse semantic labels for each image. Current methods mainly target identifying and correcting label mistakes using trained MLC models,…

In this paper, we propose a continual learning (CL) technique that is beneficial to sequential task learners by improving their retained accuracy and reducing catastrophic forgetting. The principal target of our approach is the automatic…