相关论文: Class Incremental Learning with Task-Specific Batc…
This paper investigates the problem of class-incremental object detection for agricultural applications where a model needs to learn new plant species and diseases incrementally without forgetting the previously learned ones. We adapt two…
Class-incremental learning (CIL) aims to adapt to emerging new classes without forgetting old ones. Traditional CIL models are trained from scratch to continually acquire knowledge as data evolves. Recently, pre-training has achieved…
Incremental learning requires a model to continually learn new tasks from streaming data. However, traditional fine-tuning of a well-trained deep neural network on a new task will dramatically degrade performance on the old task -- a…
Exemplar-free class-incremental learning (CIL) poses several challenges since it prohibits the rehearsal of data from previous tasks and thus suffers from catastrophic forgetting. Recent approaches to incrementally learning the classifier…
New classes arise frequently in our ever-changing world, e.g., emerging topics in social media and new types of products in e-commerce. A model should recognize new classes and meanwhile maintain discriminability over old classes. Under…
Incremental learning is a form of online learning. Incremental learning can modify the parameters and structure of the deep learning model so that the model does not forget the old knowledge while learning new knowledge. Preventing…
Deep learning architectures exhibit a critical drop of performance due to catastrophic forgetting when they are required to incrementally learn new tasks. Contemporary incremental learning frameworks focus on image classification and object…
Unsupervised continual learning aims to learn new tasks incrementally without requiring human annotations. However, most existing methods, especially those targeted on image classification, only work in a simplified scenario by assuming all…
Class-Incremental Learning (CIL) aims to enable AI models to continuously learn from sequentially arriving data of different classes over time while retaining previously acquired knowledge. Recently, Parameter-Efficient Fine-Tuning (PEFT)…
Catastrophic forgetting remains a fundamental challenge in continual learning, in which models often forget previous knowledge when fine-tuned on a new task. This issue is especially pronounced in class incremental learning (CIL), which is…
Deep neural networks often severely forget previously learned knowledge when learning new knowledge. Various continual learning (CL) methods have been proposed to handle such a catastrophic forgetting issue from different perspectives and…
In class-incremental learning (CIL) scenarios, the phenomenon of catastrophic forgetting caused by the classifier's bias towards the current task has long posed a significant challenge. It is mainly caused by the characteristic of…
In this paper, we consider a real-world scenario where a model that is trained on pre-defined classes continually encounters unlabeled data that contains both known and novel classes. The goal is to continually discover novel classes while…
This work explores class-incremental learning (CIL) for sound event detection (SED), advancing adaptability towards real-world scenarios. CIL's success in domains like computer vision inspired our SED-tailored method, addressing the unique…
In this paper we address imbalanced binary classification (IBC) tasks. Applying resampling strategies to balance the class distribution of training instances is a common approach to tackle these problems. Many state-of-the-art methods find…
Current meta-learning methods are constrained to narrow task distributions with fixed feature and label spaces, limiting applicability. Moreover, the current meta-learning literature uses key terms like "universal" and "general-purpose"…
In the realm of class-incremental learning (CIL), alleviating the catastrophic forgetting problem is a pivotal challenge. This paper discovers a counter-intuitive observation: by incorporating domain shift into CIL tasks, the forgetting…
Node classification with Graph Neural Networks (GNN) under a fixed set of labels is well known in contrast to Graph Few-Shot Class Incremental Learning (GFSCIL), which involves learning a GNN classifier as graph nodes and classes growing…
Long-tail class incremental learning (LT CIL) remains highly challenging because the scarcity of samples in tail classes not only hampers their learning but also exacerbates catastrophic forgetting under continuously evolving and imbalanced…
Deep neural networks suffer from catastrophic forgetting when continually learning new concepts. In this paper, we analyze this problem from a data imbalance point of view. We argue that the imbalance between old task and new task data…