相关论文: DualCP: Rehearsal-Free Domain-Incremental Learning…

Exemplar-free class-incremental learning using a backbone trained from scratch and starting from a small first task presents a significant challenge for continual representation learning. Prototype-based approaches, when continually…

Recently, CLIP-guided image synthesis has shown appealing performance on adapting a pre-trained source-domain generator to an unseen target domain. It does not require any target-domain samples but only the textual domain labels. The…

Class Incremental Learning (CIL) aims to enable models to learn new classes sequentially while retaining knowledge of previous ones. Although current methods have alleviated catastrophic forgetting (CF), recent studies highlight that the…

Multi-label Class-Incremental Learning aims to continuously recognize novel categories in complex scenes where multiple objects co-occur. However, existing approaches often incur high computational costs due to full-parameter fine-tuning…

Few-Shot Class-Incremental Learning (FSCIL) aims to enable deep neural networks to learn new tasks incrementally from a small number of labeled samples without forgetting previously learned tasks, closely mimicking human learning patterns.…

Collaborative learning allows participants to jointly train a model without data sharing. To update the model parameters, the central server broadcasts model parameters to the clients, and the clients send updating directions such as…

Many efforts have been devoted to designing sampling, mining, and weighting strategies in high-level deep metric learning (DML) loss objectives. However, little attention has been paid to low-level but essential data transformation. In this…

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…

This paper studies continual learning (CL) of a sequence of aspect sentiment classification(ASC) tasks in a particular CL setting called domain incremental learning (DIL). Each task is from a different domain or product. The DIL setting is…

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…

We propose Deep Companion Learning (DCL), a novel training method for Deep Neural Networks (DNNs) that enhances generalization by penalizing inconsistent model predictions compared to its historical performance. To achieve this, we train a…

Class-incremental learning (CIL) aims to train a classification model while the number of classes increases phase-by-phase. An inherent challenge of CIL is the stability-plasticity tradeoff, i.e., CIL models should keep stable to retain old…

Incremental learning (IL) aims to overcome catastrophic forgetting of previous tasks while learning new ones. Existing IL methods make strong assumptions that the incoming task type will either only increases new classes or domains (i.e.…

Differentially private (DP) contrastive learning aims to learn general-purpose representations from sensitive data, alleviating the privacy leakage concerns of organizations deploying or sharing embedding models trained on private user…

Image deconvolution is the process of recovering convolutional degraded images, which is always a hard inverse problem because of its mathematically ill-posed property. On the success of the recently proposed deep image prior (DIP), we…

Concept-oriented deep learning (CODL) is a general approach to meet the future challenges for deep learning: (1) learning with little or no external supervision, (2) coping with test examples that come from a different distribution than the…

Federated Learning (FL) has emerged as a decentralized machine learning technique, allowing clients to train a global model collaboratively without sharing private data. However, most FL studies ignore the crucial challenge of heterogeneous…

Few-shot class-incremental learning (FSCIL) aims to continuously recognize novel classes under limited data, which suffers from the key stability-plasticity dilemma: balancing the retention of old knowledge with the acquisition of new…

Although deep neural networks enable impressive visual perception performance for autonomous driving, their robustness to varying weather conditions still requires attention. When adapting these models for changed environments, such as…

Prompt learning has recently become a very efficient transfer learning paradigm for Contrastive Language Image Pretraining (CLIP) models. Compared with fine-tuning the entire encoder, prompt learning can obtain highly competitive results by…