Related papers: Class Impression for Data-free Incremental Learnin…
Class-Incremental Learning aims to update a deep classifier to learn new categories while maintaining or improving its accuracy on previously observed classes. Common methods to prevent forgetting previously learned classes include…
Data plays a pivotal role in the groundbreaking advancements in artificial intelligence. The quantitative analysis of data significantly contributes to model training, enhancing both the efficiency and quality of data utilization. However,…
In order to address real-world problems, deep learning models are jointly trained on many classes. However, in the future, some classes may become restricted due to privacy/ethical concerns, and the restricted class knowledge has to be…
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…
In a real-world setting, object instances from new classes can be continuously encountered by object detectors. When existing object detectors are applied to such scenarios, their performance on old classes deteriorates significantly. A few…
Rehearsal-based continual learning (CL) mitigates catastrophic forgetting by maintaining a subset of samples from previous tasks for replay. Existing studies primarily focus on optimizing memory storage through coreset selection strategies.…
We introduce a novel sensitivity analysis framework for large scale classification problems that can be used when a small number of instances are incrementally added or removed. For quickly updating the classifier in such a situation,…
Since the recent advent of regulations for data protection (e.g., the General Data Protection Regulation), there has been increasing demand in deleting information learned from sensitive data in pre-trained models without retraining from…
Regularization-based methods are beneficial to alleviate the catastrophic forgetting problem in class-incremental learning. With the absence of old task images, they often assume that old knowledge is well preserved if the classifier…
With the memory-resource-limited constraints, class-incremental learning (CIL) usually suffers from the "catastrophic forgetting" problem when updating the joint classification model on the arrival of newly added classes. To cope with the…
Supervised Continual learning involves updating a deep neural network (DNN) from an ever-growing stream of labeled data. While most work has focused on overcoming catastrophic forgetting, one of the major motivations behind continual…
Deep neural networks have shown superior performance in many regimes to remember familiar patterns with large amounts of data. However, the standard supervised deep learning paradigm is still limited when facing the need to learn new…
Current research on class-incremental learning primarily focuses on single-label classification tasks. However, real-world applications often involve multi-label scenarios, such as image retrieval and medical imaging. Therefore, this paper…
Small, imbalanced datasets and poor input image quality can lead to high false predictions rates with deep learning models. This paper introduces Class-Based Image Composition, an approach that allows us to reformulate training inputs…
Continual learning aims to provide intelligent agents that are capable of learning continually a sequence of tasks, building on previously learned knowledge. A key challenge in this learning paradigm is catastrophically forgetting…
Comprehensive surgical planning require complex patient-specific anatomical models. For instance, functional muskuloskeletal simulations necessitate all relevant structures to be segmented, which could be performed in real-time using deep…
The rapid proliferation of wireless devices makes robust identity authentication essential. Radio Frequency Fingerprinting (RFF) exploits device-specific, hard-to-forge physical-layer impairments for identification, and is promising for IoT…
Incremental learning methods can learn new classes continually by distilling knowledge from the last model (as a teacher model) to the current model (as a student model) in the sequentially learning process. However, these methods cannot…
Data augmentation is an essential part of the training process applied to deep learning models. The motivation is that a robust training process for deep learning models depends on large annotated datasets, which are expensive to be…
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…