Related papers: Elastic Feature Consolidation for Cold Start Exemp…
Multi-Class Incremental Learning (MCIL) aims to learn new concepts by incrementally updating a model trained on previous concepts. However, there is an inherent trade-off to effectively learning new concepts without catastrophic forgetting…
Existing continual relation learning (CRL) methods rely on plenty of labeled training data for learning a new task, which can be hard to acquire in real scenario as getting large and representative labeled data is often expensive and…
Few-shot class-incremental learning (FSCIL) presents a core challenge in continual learning, requiring models to rapidly adapt to new classes with very limited samples while mitigating catastrophic forgetting. Recent prompt-based methods,…
The goal of Continual Learning (CL) is to continuously learn from new data streams and accomplish the corresponding tasks. Previously studied CL assumes that data are given in sequence nose-to-tail for different tasks, thus indeed belonging…
Graph contrastive learning (GCL) aims to learn representations from unlabeled graph data in a self-supervised manner and has developed rapidly in recent years. However, edgelevel contrasts are not well explored by most existing GCL methods.…
One of the most significant challenges facing a few-shot learning task is the generalizability of the (meta-)model from the base to the novel categories. Most of existing few-shot learning models attempt to address this challenge by either…
This paper presents a practical and simple yet efficient method to effectively deal with the catastrophic forgetting for Class Incremental Learning (CIL) tasks. CIL tends to learn new concepts perfectly, but not at the expense of…
Continual learning (CL) learns a sequence of tasks incrementally. This paper studies the challenging CL setting of class-incremental learning (CIL). CIL has two key challenges: catastrophic forgetting (CF) and inter-task class separation…
Face verification can be regarded as a 2-class fine-grained visual recognition problem. Enhancing the feature's discriminative power is one of the key problems to improve its performance. Metric learning technology is often applied to…
The recent development of deep learning large models in medicine shows remarkable performance in medical image analysis and diagnosis, but their large number of parameters causes memory and inference latency challenges. Knowledge…
Real-world federated systems seldom operate on static data: input distributions drift while privacy rules forbid raw-data sharing. We study this setting as Federated Domain-Incremental Learning (FDIL), where (i) clients are heterogeneous,…
The focus of this study is on Unsupervised Continual Learning (UCL), as it presents an alternative to Supervised Continual Learning which needs high-quality manual labeled data. The experiments under the UCL paradigm indicate a phenomenon…
Continual learning (CL) aims to extend deep models from static and enclosed environments to dynamic and complex scenarios, enabling systems to continuously acquire new knowledge of novel categories without forgetting previously learned…
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…
The integration of large pre-trained models (PTMs) into Class-Incremental Learning (CIL) has facilitated the development of computationally efficient strategies such as First-Session Adaptation (FSA), which fine-tunes the model solely on…
Robust loss functions are crucial for training deep neural networks in the presence of label noise, yet existing approaches require extensive, dataset-specific hyperparameter tuning. In this work, we introduce Fractional Classification Loss…
We study model confidence calibration in class-incremental learning, where models learn from sequential tasks with different class sets. While existing works primarily focus on accuracy, maintaining calibrated confidence has been largely…
Most existing works on continual learning (CL) focus on overcoming the catastrophic forgetting (CF) problem, with dynamic models and replay methods performing exceptionally well. However, since current works tend to assume exclusivity or…
This paper proposes a cold start recommendation model that integrates contrastive learning, aiming to solve the problem of performance degradation of recommendation systems in cold start scenarios due to the scarcity of user and item…
The standard class-incremental continual learning setting assumes a set of tasks seen one after the other in a fixed and predefined order. This is not very realistic in federated learning environments where each client works independently…