Related papers: Simpler is Better: off-the-shelf Continual Learnin…

We introduce Continual Learning via Neural Pruning (CLNP), a new method aimed at lifelong learning in fixed capacity models based on neuronal model sparsification. In this method, subsequent tasks are trained using the inactive neurons and…

Continual learning in computer vision requires that models adapt to a continuous stream of tasks without forgetting prior knowledge, yet existing approaches often tip the balance heavily toward either plasticity or stability. We introduce…

Humans have a remarkable ability to quickly and effectively learn new concepts in a continuous manner without forgetting old knowledge. Though deep learning has made tremendous successes on various computer vision tasks, it faces challenges…

Purpose: The aim of this work is to develop a neural network training framework for continual training of small amounts of medical imaging data and create heuristics to assess training in the absence of a hold-out validation or test set.…

Image manipulation localization (IML) and general vision tasks are typically treated as two separate research directions due to the fundamental differences between manipulation-specific and semantic features. In this paper, however, we…

The requirement to repeatedly move large feature maps off- and on-chip during inference with convolutional neural networks (CNNs) imposes high costs in terms of both energy and time. In this work we explore an improved method for…

Drawing inspiration from gradient-based meta-learning methods with infinitely small gradient steps, we introduce Continuous-Time Meta-Learning (COMLN), a meta-learning algorithm where adaptation follows the dynamics of a gradient vector…

Temporal coherence is a valuable source of information in the context of optical flow estimation. However, finding a suitable motion model to leverage this information is a non-trivial task. In this paper we propose an unsupervised online…

An approach to incorporate deep learning within an iterative image reconstruction framework to reconstruct images from severely incomplete measurement data is presented. Specifically, we utilize a convolutional neural network (CNN) as a…

Data is one of the most important factors in machine learning. However, even if we have high-quality data, there is a situation in which access to the data is restricted. For example, access to the medical data from outside is strictly…

Transformer is a potentially powerful architecture for vision tasks. Although equipped with more parameters and attention mechanism, its performance is not as dominant as CNN currently. CNN is usually computationally cheaper and still the…

Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance in many computer vision tasks over the years. However, this comes at the cost of heavy computation and memory intensive network designs, suggesting potential…

The goal of continual learning (CL) is to train a model that can solve multiple tasks presented sequentially. Recent CL approaches have achieved strong performance by leveraging large pre-trained models that generalize well to downstream…

Unsupervised lifelong learning refers to the ability to learn over time while memorizing previous patterns without supervision. Although great progress has been made in this direction, existing work often assumes strong prior knowledge…

Recent works on parameter-efficient transfer learning (PETL) show the potential to adapt a pre-trained Vision Transformer to downstream recognition tasks with only a few learnable parameters. However, since they usually insert new…

We create a novel benchmark for evaluating a Deployable Lifelong Learning system for Visual Reinforcement Learning (RL) that is pretrained on a curated dataset, and propose a novel Scalable Lifelong Learning system capable of retaining…

Convolutional neural networks (CNNs) are the cutting edge model for supervised machine learning in computer vision. In recent years CNNs have outperformed traditional approaches in many computer vision tasks such as object detection, image…

A common practice in transfer learning is to initialize the downstream model weights by pre-training on a data-abundant upstream task. In object detection specifically, the feature backbone is typically initialized with Imagenet classifier…

Over recent years, a myriad of novel convolutional network architectures have been developed to advance state-of-the-art performance on challenging recognition tasks. As computational resources improve, a great deal of effort has been…

Traditional online continual learning (OCL) research has primarily focused on mitigating catastrophic forgetting with fixed and limited storage allocation throughout an agent's lifetime. However, a broad range of real-world applications are…