Related papers: Continuous Knowledge-Preserving Decomposition with…
We uncover an ever-overlooked deficiency in the prevailing Few-Shot Learning (FSL) methods: the pre-trained knowledge is indeed a confounder that limits the performance. This finding is rooted from our causal assumption: a Structural Causal…
Federated Continual Learning (FCL) has recently emerged as a crucial research area, as data from distributed clients typically arrives as a stream, requiring sequential learning. This paper explores a more practical and challenging FCL…
Class Incremental Semantic Segmentation~(CISS), within Incremental Learning for semantic segmentation, targets segmenting new categories while reducing the catastrophic forgetting on the old categories.Besides, background shifting, where…
Graph Few-Shot Class-Incremental Learning (GFSCIL) enables models to continually learn from limited samples of novel tasks after initial training on a large base dataset. Existing GFSCIL approaches typically utilize Prototypical Networks…
We propose Adapter Merging with Centroid Prototype Mapping (ACMap), an exemplar-free framework for class-incremental learning (CIL) that addresses both catastrophic forgetting and scalability. While existing methods involve a trade-off…
Class-incremental fault diagnosis requires a model to adapt to new fault classes while retaining previous knowledge. However, limited research exists for imbalanced and long-tailed data. Extracting discriminative features from few-shot…
In the field of machine learning, hyperbolic space demonstrates superior representation capabilities for hierarchical data compared to conventional Euclidean space. This work focuses on the Coarse-To-Fine Few-Shot Class-Incremental Learning…
Continual Semantic Segmentation (CSS) requires learning new classes without forgetting previously acquired knowledge, addressing the fundamental challenge of catastrophic forgetting in dense prediction tasks. However, existing CSS methods…
Continual learning allows the system to learn and adapt to new tasks while retaining the knowledge acquired from previous tasks. However, deep learning models suffer from catastrophic forgetting of knowledge learned from earlier tasks while…
Multi-label class-incremental learning (MLCIL) continuously expands the label space while recognizing multiple co-occurring classes, making it prone to catastrophic forgetting and high false-positive rates (FPR). Extending CLIP to MLCIL is…
Current deep learning models often suffer from catastrophic forgetting of old knowledge when continually learning new knowledge. Existing strategies to alleviate this issue often fix the trade-off between keeping old knowledge (stability)…
How to adapt a pre-trained model continuously for sequential tasks with different prediction class labels and domains and finally learn a generalizable model across diverse tasks is a long-lasting challenge. Continual learning (CL) has…
Continual learning (CL) has traditionally focused on minimizing exemplar memory, a constraint often misaligned with modern systems where GPU time, not storage, is the primary bottleneck. This paper challenges this paradigm by investigating…
Graph class-incremental learning (GCIL) allows graph neural networks (GNNs) to adapt to evolving graph analytical tasks by incrementally learning new class knowledge while retaining knowledge of old classes. Existing GCIL methods primarily…
Despite significant progress in continual learning ranging from architectural novelty to clever strategies for mitigating catastrophic forgetting most existing methods rest on a strong but unrealistic assumption the availability of labeled…
To effectively manage the complexities of real-world dynamic environments, continual learning must incrementally acquire, update, and accumulate knowledge from a stream of tasks of different nature without suffering from catastrophic…
Continual learning is an emerging topic in the field of deep learning, where a model is expected to learn continuously for new upcoming tasks without forgetting previous experiences. This field has witnessed numerous advancements, but few…
Real-world systems must continuously adapt to novel concepts from limited data without forgetting previously acquired knowledge. While Few-Shot Class-Incremental Learning (FSCIL) is established in computer vision, its application to tabular…
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…
Reinforcement Learning enables agents to learn optimal behaviors through interactions with environments. However, real-world environments are typically non-stationary, requiring agents to continuously adapt to new tasks and changing…