Related papers: Evolving Knowledge Mining for Class Incremental Se…

Deep Learning has emerged as a promising approach for skin lesion analysis. However, existing methods mostly rely on fully supervised learning, requiring extensive labeled data, which is challenging and costly to obtain. To alleviate this…

In spite of remarkable success of the convolutional neural networks on semantic segmentation, they suffer from catastrophic forgetting: a significant performance drop for the already learned classes when new classes are added on the data,…

Improving the performance of semantic segmentation models using multispectral information is crucial, especially for environments with low-light and adverse conditions. Multi-modal fusion techniques pursue either the learning of…

Class Incremental Learning (CIL) aims to continuously learn new categories while retaining the knowledge of old ones. Pre-trained models (PTMs) show promising capabilities in CIL. However, existing approaches that apply lightweight…

Continual learning is a challenging problem in which models need to be trained on non-stationary data across sequential tasks for class-incremental learning. While previous methods have focused on using either regularization or…

Continual learning of new knowledge over time is one desirable capability for intelligent systems to recognize more and more classes of objects. Without or with very limited amount of old data stored, an intelligent system often…

Conventional federated learning (FL) assumes a closed world with a fixed total number of clients. In contrast, new clients continuously join the FL process in real-world scenarios, introducing new knowledge. This raises two critical…

We present a novel information-theoretic approach to introduce dependency among features of a deep convolutional neural network (CNN). The core idea of our proposed method, called MUSE, is to combine MUtual information and SElf-information…

Class-Incremental Learning (CIL) enables learning systems to continuously adapt to evolving data streams. With the advancement of pre-training, leveraging pre-trained vision-language models (e.g., CLIP) offers a promising starting point for…

Class Incremental Learning (CIL) poses a fundamental challenge: maintaining a balance between the plasticity required to learn new tasks and the stability needed to prevent catastrophic forgetting. While expansion-based methods effectively…

In this work, we explore data augmentations for knowledge distillation on semantic segmentation. To avoid over-fitting to the noise in the teacher network, a large number of training examples is essential for knowledge distillation.…

The large-scale pretrained model CLIP, trained on 400 million image-text pairs, offers a promising paradigm for tackling vision tasks, albeit at the image level. Later works, such as DenseCLIP and LSeg, extend this paradigm to dense…

New categories may be introduced over time, or existing categories may need to be reclassified. Class incremental learning (CIL) is employed for the gradual acquisition of knowledge about new categories while preserving information about…

Knowledge distillation is an effective method to transfer the knowledge from the cumbersome teacher model to the lightweight student model. Online knowledge distillation uses the ensembled prediction results of multiple student models as…

The recent advances of hardware technology have made the intelligent analysis equipped at the front-end with deep learning more prevailing and practical. To better enable the intelligent sensing at the front-end, instead of compressing and…

Many deep learning applications, like keyword spotting, require the incorporation of new concepts (classes) over time, referred to as Class Incremental Learning (CIL). The major challenge in CIL is catastrophic forgetting, i.e., preserving…

Continual Learning seeks to develop a model capable of incrementally assimilating new information while retaining prior knowledge. However, current research predominantly addresses a straightforward learning context, wherein all data…

Recent advancements in Neural Machine Translation (NMT) have significantly improved translation quality. However, the increasing size and complexity of state-of-the-art models present significant challenges for deployment on…

Large language models (LLMs) are proficient in capturing factual knowledge across various domains. However, refining their capabilities on previously seen knowledge or integrating new knowledge from external sources remains a significant…

A novel energy-efficient edge computing paradigm is proposed for real-time deep learning-based image upsampling applications. State-of-the-art deep learning solutions for image upsampling are currently trained using either resize or…