Related papers: Ternary Feature Masks: zero-forgetting for task-in…
We study class-incremental learning, a training setup in which new classes of data are observed over time for the model to learn from. Despite the straightforward problem formulation, the naive application of classification models to…
In Continual Learning, a Neural Network is trained on a stream of data whose distribution shifts over time. Under these assumptions, it is especially challenging to improve on classes appearing later in the stream while remaining accurate…
Data augmentation is an effective technique for improving the performance of machine learning models. However, it has not been explored as extensively in natural language processing (NLP) as it has in computer vision. In this paper, we…
Inspired by Regularized Lottery Ticket Hypothesis (RLTH), which states that competitive smooth (non-binary) subnetworks exist within a dense network in continual learning tasks, we investigate two proposed architecture-based continual…
Incremental learning is a form of online learning. Incremental learning can modify the parameters and structure of the deep learning model so that the model does not forget the old knowledge while learning new knowledge. Preventing…
Deep neural networks are used in many state-of-the-art systems for machine perception. Once a network is trained to do a specific task, e.g., bird classification, it cannot easily be trained to do new tasks, e.g., incrementally learning to…
A deeper network structure generally handles more complicated non-linearity and performs more competitively. Nowadays, advanced network designs often contain a large number of repetitive structures (e.g., Transformer). They empower the…
The ability to learn new concepts while preserve the learned knowledge is desirable for learning systems in Class-Incremental Learning (CIL). Recently, feature expansion of the model become a prevalent solution for CIL, where the old…
In this paper, we consider the problem of fine-grained image retrieval in an incremental setting, when new categories are added over time. On the one hand, repeatedly training the representation on the extended dataset is time-consuming. On…
Incremental learning aims to learn new tasks sequentially without forgetting the previously learned ones. Most of the existing incremental learning methods for audio focus on training the model from scratch on the initial task, and the same…
Neural networks (NNs) whose subnetworks implement reusable functions are expected to offer numerous advantages, including compositionality through efficient recombination of functional building blocks, interpretability, preventing…
Deep neural networks have revolutionized numerous research fields and applications. Despite their widespread success, a fundamental limitation known as catastrophic forgetting remains, where models fail to retain their ability to perform…
Deep learning methods are successfully used in applications pertaining to ubiquitous computing, health, and well-being. Specifically, the area of human activity recognition (HAR) is primarily transformed by the convolutional and recurrent…
Artificial neural networks have exceeded human-level performance in accomplishing several individual tasks (e.g. voice recognition, object recognition, and video games). However, such success remains modest compared to human intelligence…
Incremental class learning, a scenario in continual learning context where classes and their training data are sequentially and disjointedly observed, challenges a problem widely known as catastrophic forgetting. In this work, we propose a…
Removing information from a machine learning model is a non-trivial task that requires to partially revert the training process. This task is unavoidable when sensitive data, such as credit card numbers or passwords, accidentally enter the…
The ability to remove features from the input of machine learning models is very important to understand and interpret model predictions. However, this is non-trivial for vision models since masking out parts of the input image typically…
We introduce a tensor-based model of shared representation for meta-learning from a diverse set of tasks. Prior works on learning linear representations for meta-learning assume that there is a common shared representation across different…
In recent years, Deep Neural Networks (DNN) have emerged as a practical method for image recognition. The raw data, which contain sensitive information, are generally exploited within the training process. However, when the training process…
This paper describes an application of reinforcement learning to the mention detection task. We define a novel action-based formulation for the mention detection task, in which a model can flexibly revise past labeling decisions by grouping…