相关论文: LightCL: Compact Continual Learning with Low Memor…

The goal of continual learning is to improve the performance of recognition models in learning sequentially arrived data. Although most existing works are established on the premise of learning from scratch, growing efforts have been…

Nowadays, real-world data, including graph-structure data, often arrives in a streaming manner, which means that learning systems need to continuously acquire new knowledge without forgetting previously learned information. Although…

Humans and animals learn throughout their lives from limited amounts of sensed data, both with and without supervision. Autonomous, intelligent robots of the future are often expected to do the same. The existing continual learning (CL)…

The proliferation of end devices has led to a distributed computing paradigm, wherein on-device machine learning models continuously process diverse data generated by these devices. The dynamic nature of this data, characterized by…

We introduce Flashback Learning (FL), a novel method designed to harmonize the stability and plasticity of models in Continual Learning (CL). Unlike prior approaches that primarily focus on regularizing model updates to preserve old…

We address the Continual Learning (CL) problem, wherein a model must learn a sequence of tasks from non-stationary distributions while preserving prior knowledge upon encountering new experiences. With the advancement of foundation models,…

Rapid development of large-scale pre-training has resulted in foundation models that can act as effective feature extractors on a variety of downstream tasks and domains. Motivated by this, we study the efficacy of pre-trained vision models…

Humans learn continually throughout their lifespan by accumulating diverse knowledge and fine-tuning it for future tasks. When presented with a similar goal, neural networks suffer from catastrophic forgetting if data distributions across…

Continual learning (CL) -- the ability to continuously learn, building on previously acquired knowledge -- is a natural requirement for long-lived autonomous reinforcement learning (RL) agents. While building such agents, one needs to…

Continual learning (CL) aims to constantly learn new knowledge over time while avoiding catastrophic forgetting on old tasks. In this work, we focus on continual text classification under the class-incremental setting. Recent CL studies…

In streaming scenarios, models must learn continuously, adapting to concept drifts without erasing previously acquired knowledge. However, existing research communities address these challenges in isolation. Continual Learning (CL) focuses…

The exponential growth of Internet-connected devices has presented challenges to traditional centralized computing systems due to latency and bandwidth limitations. Edge computing has evolved to address these difficulties by bringing…

Existing Continual Learning (CL) solutions only partially address the constraints on power, memory and computation of the deep learning models when deployed on low-power embedded CPUs. In this paper, we propose a CL solution that embraces…

Continual lifelong learning is essential to many applications. In this paper, we propose a simple but effective approach to continual deep learning. Our approach leverages the principles of deep model compression, critical weights…

Deploying large language models (LLMs) on edge devices is crucial for delivering fast responses and ensuring data privacy. However, the limited storage, weight, and power of edge devices make it difficult to deploy LLM-powered applications.…

Simultaneous localization and mapping (SLAM) with implicit neural representations has received extensive attention due to the expressive representation power and the innovative paradigm of continual learning. However, deploying such a…

Continual learning is the ability to acquire new knowledge without forgetting the previously learned one, assuming no further access to past training data. Neural network approximators trained with gradient descent are known to fail in this…

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…

Efforts to overcome catastrophic forgetting have primarily centered around developing more effective Continual Learning (CL) methods. In contrast, less attention was devoted to analyzing the role of network architecture design (e.g.,…

We propose an approach for anytime continual learning (AnytimeCL) for open vocabulary image classification. The AnytimeCL problem aims to break away from batch training and rigid models by requiring that a system can predict any set of…