Related papers: When Video Classification Meets Incremental Classe…

In this work, we focus on continual semantic segmentation (CSS), where segmentation networks are required to continuously learn new classes without erasing knowledge of previously learned ones. Although storing images of old classes and…

Predictive learning ideally builds the world model of physical processes in one or more given environments. Typical setups assume that we can collect data from all environments at all times. In practice, however, different prediction tasks…

Image segmentation based on continual learning exhibits a critical drop of performance, mainly due to catastrophic forgetting and background shift, as they are required to incorporate new classes continually. In this paper, we propose a…

Video representation learning is a vital problem for classification task. Recently, a promising unsupervised paradigm termed self-supervised learning has emerged, which explores inherent supervisory signals implied in massive data for…

Over the past few years, various tasks involving videos such as classification, description, summarization and question answering have received a lot of attention. Current models for these tasks compute an encoding of the video by treating…

Class-Incremental Learning aims to update a deep classifier to learn new categories while maintaining or improving its accuracy on previously observed classes. Common methods to prevent forgetting previously learned classes include…

Continual lifelong learning is essential to many applications. In this paper, we propose a simple but effective approach to continual deep learning. Our approach leverages the principles of deep model compression, critical weights…

Temporal action segmentation classifies the action of each frame in (long) video sequences. Due to the high cost of frame-wise labeling, we propose the first semi-supervised method for temporal action segmentation. Our method hinges on…

Class-incremental learning (CIL) aims to develop a learning system that can continually learn new classes from a data stream without forgetting previously learned classes. When learning classes incrementally, the classifier must be…

Deep learning approaches are successful in a wide range of AI problems and in particular for visual recognition tasks. However, there are still open problems among which is the capacity to handle streams of visual information and the…

We propose a novel application of Transfer Learning to classify video-frame sequences over multiple classes. This is a pre-weighted model that does not require to train a fresh CNN. This representation is achieved with the advent of "deep…

This paper addresses the problem of video summarization. Given an input video, the goal is to select a subset of the frames to create a summary video that optimally captures the important information of the input video. With the large…

Over the past years, semantic segmentation, as many other tasks in computer vision, benefited from the progress in deep neural networks, resulting in significantly improved performance. However, deep architectures trained with…

The current research focus on Content-Based Video Retrieval requires higher-level video representation describing the long-range semantic dependencies of relevant incidents, events, etc. However, existing methods commonly process the frames…

We consider object recognition in the context of lifelong learning, where a robotic agent learns to discriminate between a growing number of object classes as it accumulates experience about the environment. We propose an incremental…

Continual learning aims to update a model so that it can sequentially learn new tasks without forgetting previously acquired knowledge. Recent continual learning approaches often leverage the vision-language model CLIP for its…

Scarcity of data and incremental learning of new tasks pose two major bottlenecks for many modern computer vision algorithms. The phenomenon of catastrophic forgetting, i.e., the model's inability to classify previously learned data after…

Most existing works on continual learning (CL) focus on overcoming the catastrophic forgetting (CF) problem, with dynamic models and replay methods performing exceptionally well. However, since current works tend to assume exclusivity or…

Online continual learning for image classification studies the problem of learning to classify images from an online stream of data and tasks, where tasks may include new classes (class incremental) or data nonstationarity (domain…

Continuously learning new classes without catastrophic forgetting is a challenging problem for on-device environmental sound classification given the restrictions on computation resources (e.g., model size, running memory). To address this…