相关论文: Attribution-aware Weight Transfer: A Warm-Start In…

Modern machine learning systems need to be able to cope with constantly arriving and changing data. Two main areas of research dealing with such scenarios are continual learning and data stream mining. Continual learning focuses on…

Humans have the ability to accumulate knowledge of new tasks in varying conditions, but deep neural networks often suffer from catastrophic forgetting of previously learned knowledge after learning a new task. Many recent methods focus on…

Continual learning is crucial for applying machine learning in challenging, dynamic, and often resource-constrained environments. However, catastrophic forgetting - overwriting previously learned knowledge when new information is acquired -…

Few-shot class-incremental learning(FSCIL) focuses on designing learning algorithms that can continually learn a sequence of new tasks from a few samples without forgetting old ones. The difficulties are that training on a sequence of…

In many computer vision classification tasks, class priors at test time often differ from priors on the training set. In the case of such prior shift, classifiers must be adapted correspondingly to maintain close to optimal performance.…

Recently, the Transformer machine translation system has shown strong results by stacking attention layers on both the source and target-language sides. But the inference of this model is slow due to the heavy use of dot-product attention…

Recently, embedding techniques have achieved impressive success in recommender systems. However, the embedding techniques are data demanding and suffer from the cold-start problem. Especially, for the cold-start item which only has limited…

Continual semantic segmentation (CSS) is a cornerstone task in computer vision that enables a large number of downstream applications, but faces the catastrophic forgetting challenge. In conventional class-incremental semantic segmentation…

Semi-supervised semantic segmentation (SSSS) aims to improve segmentation performance by utilizing large amounts of unlabeled data with limited labeled samples. Existing methods often suffer from coupling, where over-reliance on initial…

Deep neural networks suffer from the major limitation of catastrophic forgetting old tasks when learning new ones. In this paper we focus on class incremental continual learning in semantic segmentation, where new categories are made…

How can we reuse existing knowledge, in the form of available datasets, when solving a new and apparently unrelated target task from a set of unlabeled data? In this work we make a first contribution to answer this question in the context…

Transfer learning is a problem defined over two domains. These two domains share the same feature space and class label space, but have significantly different distributions. One domain has sufficient labels, named as source domain, and the…

Appropriate weight initialization has been of key importance to successfully train neural networks. Recently, batch normalization has diminished the role of weight initialization by simply normalizing each layer based on batch statistics.…

Intermediate task transfer learning can greatly improve model performance. If, for example, one has little training data for emotion detection, first fine-tuning a language model on a sentiment classification dataset may improve performance…

Contextual biasing enables speech recognizers to transcribe important phrases in the speaker's context, such as contact names, even if they are rare in, or absent from, the training data. Attention-based biasing is a leading approach which…

Active preference learning offers an efficient approach to modeling preferences, but it is hindered by the cold-start problem, which leads to a marked decline in performance when no initial labeled data are available. While cold-start…

Embedding & MLP has become a paradigm for modern large-scale recommendation system. However, this paradigm suffers from the cold-start problem which will seriously compromise the ecological health of recommendation systems. This paper…

Many sequential recommender systems suffer from the cold start problem, where items with few or no interactions cannot be effectively used by the model due to the absence of a trained embedding. Content-based approaches, which leverage item…

Class-agnostic image segmentation is a crucial component in automating image editing workflows, especially in contexts where object selection traditionally involves interactive tools. Existing methods in the literature often adhere to…

Few-shot class incremental learning (FSCIL) portrays the problem of learning new concepts gradually, where only a few examples per concept are available to the learner. Due to the limited number of examples for training, the techniques…