Related papers: Joint Input and Output Coordination for Class-Incr…
With the memory-resource-limited constraints, class-incremental learning (CIL) usually suffers from the "catastrophic forgetting" problem when updating the joint classification model on the arrival of newly added classes. To cope with the…
Current deep learning models often suffer from catastrophic forgetting of old knowledge when continually learning new knowledge. Existing strategies to alleviate this issue often fix the trade-off between keeping old knowledge (stability)…
Most deep reinforcement learning algorithms are data inefficient in complex and rich environments, limiting their applicability to many scenarios. One direction for improving data efficiency is multitask learning with shared neural network…
How to enable learnability for new classes while keeping the capability well on old classes has been a crucial challenge for class incremental learning. Beyond the normal case, long-tail class incremental learning and few-shot class…
Deep learning architectures have shown remarkable results in scene understanding problems, however they exhibit a critical drop of performances when they are required to learn incrementally new tasks without forgetting old ones. This…
Continual learning is the ability to sequentially learn over time by accommodating knowledge while retaining previously learned experiences. Neural networks can learn multiple tasks when trained on them jointly, but cannot maintain…
This paper introduces INCPrompt, an innovative continual learning solution that effectively addresses catastrophic forgetting. INCPrompt's key innovation lies in its use of adaptive key-learner and task-aware prompts that capture…
Continual learning refers to a dynamical framework in which a model receives a stream of non-stationary data over time and must adapt to new data while preserving previously acquired knowledge. Unluckily, neural networks fail to meet these…
The ability to learn from incrementally arriving data is essential for any life-long learning system. However, standard deep neural networks forget the knowledge about the old tasks, a phenomenon called catastrophic forgetting, when trained…
Machine Learning models in real-world applications must continuously learn new tasks to adapt to shifts in the data-generating distribution. Yet, for Continual Learning (CL), models often struggle to balance learning new tasks (plasticity)…
Continual learning (CL) remains a significant challenge for deep neural networks, as it is prone to forgetting previously acquired knowledge. Several approaches have been proposed in the literature, such as experience rehearsal,…
Sequential learning of tasks using gradient descent leads to an unremitting decline in the accuracy of tasks for which training data is no longer available, termed catastrophic forgetting. Generative models have been explored as a means to…
Deep learning models generally display catastrophic forgetting when learning new data continuously. Many incremental learning approaches address this problem by reusing data from previous tasks while learning new tasks. However, the direct…
Lifelong learning is a very important step toward realizing robust autonomous artificial agents. Neural networks are the main engine of deep learning, which is the current state-of-the-art technique in formulating adaptive artificial…
Acquiring new knowledge without forgetting what has been learned in a sequence of tasks is the central focus of continual learning (CL). While tasks arrive sequentially, the training data are often prepared and annotated independently,…
One of the well-known challenges in computer vision tasks is the visual diversity of images, which could result in an agreement or disagreement between the learned knowledge and the visual content exhibited by the current observation. In…
This paper studies the challenging continual learning (CL) setting of Class Incremental Learning (CIL). CIL learns a sequence of tasks consisting of disjoint sets of concepts or classes. At any time, a single model is built that can be…
In this work, we introduce JDCL - a new method for continual learning with generative rehearsal based on joint diffusion models. Neural networks suffer from catastrophic forgetting defined as abrupt loss in the model's performance when…
Multitask learning is a methodology to boost generalization performance and also reduce computational intensity and memory usage. However, learning multiple tasks simultaneously can be more difficult than learning a single task because it…
Continual learning (CL) learns a sequence of tasks incrementally. There are two popular CL settings, class incremental learning (CIL) and task incremental learning (TIL). A major challenge of CL is catastrophic forgetting (CF). While a…