相关论文: Inherit with Distillation and Evolve with Contrast…

Incremental semantic segmentation aims to continually learn the segmentation of new coming classes without accessing the training data of previously learned classes. However, most current methods fail to address catastrophic forgetting and…

The performance of autoregressive models on natural language generation tasks has dramatically improved due to the adoption of deep, self-attentive architectures. However, these gains have come at the cost of hindering inference speed,…

Distributed learning on the edge often comprises self-centered devices (SCD) which learn local tasks independently and are unwilling to contribute to the performance of other SDCs. How do we achieve forward transfer at zero cost for the…

Class-incremental with repetition (CIR), where previously trained classes repeatedly introduced in future tasks, is a more realistic scenario than the traditional class incremental setup, which assumes that each task contains unseen…

In class-incremental learning, the model is expected to learn new classes continually while maintaining knowledge on previous classes. The challenge here lies in preserving the model's ability to effectively represent prior classes in the…

Continual learning aims to acquire new knowledge while retaining past information. Class-incremental learning (CIL) presents a challenging scenario where classes are introduced sequentially. For video data, the task becomes more complex…

Image-text contrastive models like CLIP have wide applications in zero-shot classification, image-text retrieval, and transfer learning. However, they often struggle on compositional visio-linguistic tasks (e.g., attribute-binding or…

Post-training endows pretrained LLMs with a variety of desirable skills, including instruction-following, reasoning, and others. However, these post-trained LLMs only encode knowledge up to a cut-off date, necessitating continual…

Exemplar-free incremental learning is extremely challenging due to inaccessibility of data from old tasks. In this paper, we attempt to exploit the knowledge encoded in a previously trained classification model to handle the catastrophic…

We study the new task of class-incremental Novel Class Discovery (class-iNCD), which refers to the problem of discovering novel categories in an unlabelled data set by leveraging a pre-trained model that has been trained on a labelled data…

Neural networks notoriously suffer from the problem of catastrophic forgetting, the phenomenon of forgetting the past knowledge when acquiring new knowledge. Overcoming catastrophic forgetting is of significant importance to emulate the…

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…

We investigate the problem of incremental learning for object counting, where a method must learn to count a variety of object classes from a sequence of datasets. A na\"ive approach to incremental object counting would suffer from…

Referring image segmentation (RIS) requires accurate segmentation of target regions in images according to language descriptions, which is a cross-modal task integrating vision and language. Existing RIS methods typically employ large-scale…

Unsupervised Continual Learning (UCL) is a burgeoning field in machine learning, focusing on enabling neural networks to sequentially learn tasks without explicit label information. Catastrophic Forgetting (CF), where models forget…

Class-incremental learning (CIL) aims to develop a learning system that can continually learn new classes from a data stream without forgetting previously learned classes. When learning classes incrementally, the classifier must be…

Class-incremental learning (CIL) enables continuous learning of new classes while mitigating catastrophic forgetting of old ones. For the performance breakthrough of CIL, it is essential yet challenging to effectively refine past knowledge…

Multi-task learns multiple tasks, while sharing knowledge and computation among them. However, it suffers from catastrophic forgetting of previous knowledge when learned incrementally without access to the old data. Most existing object…

Contrastive Language-Image Pre-training (CLIP) has been shown to improve zero-shot generalization capabilities of language and vision models. In this paper, we extend CLIP for efficient knowledge distillation, by utilizing embeddings as…

This paper presents a practical and simple yet efficient method to effectively deal with the catastrophic forgetting for Class Incremental Learning (CIL) tasks. CIL tends to learn new concepts perfectly, but not at the expense of…