Related papers: On the importance of cross-task features for class…
Incremental learning is useful if an AI agent needs to integrate data from a stream. The problem is non trivial if the agent runs on a limited computational budget and has a bounded memory of past data. In a deep learning approach, the…
While robot learning has demonstrated promising results for enabling robots to automatically acquire new skills, a critical challenge in deploying learning-based systems is scale: acquiring enough data for the robot to effectively…
Deep neural networks (DNNs) often suffer from "catastrophic forgetting" during incremental learning (IL) --- an abrupt degradation of performance on the original set of classes when the training objective is adapted to a newly added set of…
Continual learning aims to alleviate catastrophic forgetting when handling consecutive tasks under non-stationary distributions. Gradient-based meta-learning algorithms have shown the capability to implicitly solve the transfer-interference…
Continual learning (CL) aims to train models on a sequence of tasks while retaining performance on previously learned ones. A core challenge in this setting is catastrophic forgetting, where new learning interferes with past knowledge.…
Class-incremental learning is a challenging problem, where the goal is to train a model that can classify data from an increasing number of classes over time. With the advancement of vision-language pre-trained models such as CLIP, they…
In this paper we consider a problem known as multi-task learning, consisting of fitting a set of classifier or regression functions intended for solving different tasks. In our novel formulation, we couple the parameters of these functions,…
We introduce intra-class memorability, where certain images within the same class are more memorable than others despite shared category characteristics. To investigate what features make one object instance more memorable than others, we…
Exemplar-Free Class Incremental Learning is a highly challenging setting where replay memory is unavailable. Methods relying on frozen feature extractors have drawn attention recently in this setting due to their impressive performances and…
Although well-trained deep neural networks have shown remarkable performance on numerous tasks, they rapidly forget what they have learned as soon as they begin to learn with additional data with the previous data stop being provided. In…
The field of Continual Learning investigates the ability to learn consecutive tasks without losing performance on those previously learned. Its focus has been mainly on incremental classification tasks. We believe that research in continual…
Continual self-supervised learning (CSSL) learns a series of tasks sequentially on the unlabeled data. Two main challenges of continual learning are catastrophic forgetting and task confusion. While CSSL problem has been studied to address…
Continual learning aims to provide intelligent agents capable of learning multiple tasks sequentially with neural networks. One of its main challenging, catastrophic forgetting, is caused by the neural networks non-optimal ability to learn…
Continual learning requires the model to maintain the learned knowledge while learning from a non-i.i.d data stream continually. Due to the single-pass training setting, online continual learning is very challenging, but it is closer to the…
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…
In the past, continual learning (CL) was mostly concerned with the problem of catastrophic forgetting in neural networks, that arises when incrementally learning a sequence of tasks. Current CL methods function within the confines of…
Exemplar-based class-incremental learning is to recognize new classes while not forgetting old ones, whose samples can only be saved in limited memory. The ratio fluctuation of new samples to old exemplars, which is caused by the variation…
This paper investigates the problem of class-incremental object detection for agricultural applications where a model needs to learn new plant species and diseases incrementally without forgetting the previously learned ones. We adapt two…
For most real-world applications, robots need to adapt and learn continually with limited data in their environments. In this paper, we consider the problem of Few-Shot class Incremental Learning (FSIL), in which an AI agent is required to…
Catastrophic forgetting is one of the major challenges on the road for continual learning systems, which are presented with an on-line stream of tasks. The field has attracted considerable interest and a diverse set of methods have been…