Related papers: Task-recency bias strikes back: Adapting covarianc…
Aiming to incrementally learn new classes with only few samples while preserving the knowledge of base (old) classes, few-shot class-incremental learning (FSCIL) faces several challenges, such as overfitting and catastrophic forgetting.…
Continual learning aims to learn a sequence of tasks from dynamic data distributions. Without accessing to the old training samples, knowledge transfer from the old tasks to each new task is difficult to determine, which might be either…
Real-world scenarios are usually accompanied by continuously appearing classes with scare labeled samples, which require the machine learning model to incrementally learn new classes and maintain the knowledge of base classes. In this…
End-to-end vision-based imitation learning has demonstrated promising results in autonomous driving by learning control commands directly from expert demonstrations. However, traditional approaches rely on either regressionbased models,…
Class-Incremental Learning (CIL) aims to learn new classes sequentially while retaining the knowledge of previously learned classes. Recently, pre-trained models (PTMs) combined with parameter-efficient fine-tuning (PEFT) have shown…
Online task-free continual learning (OTFCL) is a more challenging variant of continual learning which emphasizes the gradual shift of task boundaries and learns in an online mode. Existing methods rely on a memory buffer composed of old…
In this paper, we revisited the role of data augmentation in contrastive learning for sequential recommendation, revealing its inherent bias against low-frequency items and sparse user behaviors. To address this limitation, we proposed…
This paper studies the problem of class-incremental learning (CIL), a core setting within continual learning where a model learns a sequence of tasks, each containing a distinct set of classes. Traditional CIL methods, which do not leverage…
Meta-learning for few-shot learning entails acquiring a prior over previous tasks and experiences, such that new tasks be learned from small amounts of data. However, a critical challenge in few-shot learning is task ambiguity: even when a…
Few-shot class-incremental learning (FSCIL) aims to learn progressively about new classes with very few labeled samples, without forgetting the knowledge of already learnt classes. FSCIL suffers from two major challenges: (i) over-fitting…
We propose a new method for exemplar-free class incremental training of ViTs. The main challenge of exemplar-free continual learning is maintaining plasticity of the learner without causing catastrophic forgetting of previously learned…
Recently, Transformer-based robotic manipulation methods utilize multi-view spatial representations and language instructions to learn robot motion trajectories by leveraging numerous robot demonstrations. However, the collection of robot…
Autoregressive video diffusion models hold promise for world simulation but are vulnerable to exposure bias arising from the train-test mismatch. While recent works address this via post-training, they typically rely on a bidirectional…
Few-shot class-incremental Learning (FSCIL) enables models to learn new classes from limited data while retaining performance on previously learned classes. Traditional FSCIL methods often require fine-tuning parameters with limited new…
Deep Neural Networks (or DNNs) must constantly cope with distribution changes in the input data when the task of interest or the data collection protocol changes. Retraining a network from scratch to combat this issue poses a significant…
Continual Learning enables models to learn and adapt to new tasks while retaining prior knowledge. Introducing new tasks, however, can naturally lead to feature entanglement across tasks, limiting the model's capability to distinguish…
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…
Humans are capable of learning new tasks without forgetting previous ones, while neural networks fail due to catastrophic forgetting between new and previously-learned tasks. We consider a class-incremental setting which means that the…
Few-shot class-incremental learning (FSCIL) is designed to incrementally recognize novel classes with only few training samples after the (pre-)training on base classes with sufficient samples, which focuses on both base-class performance…
Federated Class Incremental Learning (FCIL) is a critical yet largely underexplored issue that deals with the dynamic incorporation of new classes within federated learning (FL). Existing methods often employ generative adversarial networks…