相关论文: Few-Shot Incremental Learning with Continually Evo…
Few-shot class-incremental learning is crucial for developing scalable and adaptive intelligent systems, as it enables models to acquire new classes with minimal annotated data while safeguarding the previously accumulated knowledge.…
Deep learning models have demonstrated exceptional performance in a variety of real-world applications. These successes are often attributed to strong base models that can generalize to novel tasks with limited supporting data while keeping…
While many FSCIL studies have been undertaken, achieving satisfactory performance, especially during incremental sessions, has remained challenging. One prominent challenge is that the encoder, trained with an ample base session training…
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…
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…
The proliferation of Few-Shot Class Incremental Learning (FSCIL) methodologies has highlighted the critical challenge of maintaining robust anti-amnesia capabilities in FSCIL learners. In this paper, we present a novel conceptualization of…
Few-shot class-incremental learning (FSCIL) aims to acquire knowledge from novel classes with limited samples while retaining information about base classes. Existing methods address catastrophic forgetting and overfitting by freezing the…
Exemplar-free class incremental learning (EF-CIL) is a nontrivial task that requires continuously enriching model capability with new classes while maintaining previously learned knowledge without storing and replaying any old class…
Continual learning and few-shot learning are important frontiers in progress toward broader Machine Learning (ML) capabilities. Recently, there has been intense interest in combining both. One of the first examples to do so was the…
Deep models, e.g., CNNs and Vision Transformers, have achieved impressive achievements in many vision tasks in the closed world. However, novel classes emerge from time to time in our ever-changing world, requiring a learning system to…
Modern computer vision applications suffer from catastrophic forgetting when incrementally learning new concepts over time. The most successful approaches to alleviate this forgetting require extensive replay of previously seen data, which…
For real-world applications, robots will need to continually learn in their environments through limited interactions with their users. Toward this, previous works in few-shot class incremental learning (FSCIL) and active class selection…
Few-shot class-incremental learning (FSCIL) has recently attracted extensive attention in various areas. Existing FSCIL methods highly depend on the robustness of the feature backbone pre-trained on base classes. In recent years, different…
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…
Few-Shot Class-Incremental Learning (FSCIL) must contend with the dual challenge of learning new classes from scarce samples while preserving old class knowledge. Existing methods use the frozen feature extractor and class-averaged…
Despite the outstanding performance in many individual tasks, deep neural networks suffer from catastrophic forgetting when learning from continuous data streams in real-world scenarios. Current Non-Exemplar Class-Incremental Learning…
Incremental learning remains a critical challenge in machine learning, as models often struggle with catastrophic forgetting -the tendency to lose previously acquired knowledge when learning new information. These challenges are even more…
Learning from large-scale pre-trained models with strong generalization ability has shown remarkable success in a wide range of downstream tasks recently, but it is still underexplored in the challenging few-shot class-incremental learning…
Existing Class Incremental Learning (CIL) methods are based on a supervised classification framework sensitive to data labels. When updating them based on the new class data, they suffer from catastrophic forgetting: the model cannot…
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…