Related papers: Slightly Shift New Classes to Remember Old Classes…

Non-exemplar class incremental learning aims to learn both the new and old tasks without accessing any training data from the past. This strict restriction enlarges the difficulty of alleviating catastrophic forgetting since all techniques…

Non-exemplar class-incremental learning refers to classifying new and old classes without storing samples of old classes. Since only new class samples are available for optimization, it often occurs catastrophic forgetting of old knowledge.…

Class-incremental learning requires a learning system to continually learn knowledge of new classes and meanwhile try to preserve previously learned knowledge of old classes. As current state-of-the-art methods based on Vision-Language…

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…

In this work, we tackle the problem of video classincremental learning (VCIL). Many existing VCIL methods mitigate catastrophic forgetting by rehearsal training with a few temporally dense samples stored in episodic memory, which is…

Incremental learning enables artificial agents to learn from sequential data. While important progress was made by exploiting deep neural networks, incremental learning remains very challenging. This is particularly the case when no memory…

As neural networks are increasingly deployed in dynamic environments, they face the challenge of catastrophic forgetting, the tendency to overwrite previously learned knowledge when adapting to new tasks, resulting in severe performance…

Improving existing neural network architectures can involve several design choices such as manipulating the loss functions, employing a diverse learning strategy, exploiting gradient evolution at training time, optimizing the network…

Recent advances in Multimodal Large Language Models (MLLMs) have improved image recognition and reasoning, but video-related tasks remain challenging due to memory constraints from dense frame processing. Existing Video Moment Retrieval…

This work focuses on tackling the challenging but realistic visual task of Incremental Few-Shot Learning (IFSL), which requires a model to continually learn novel classes from only a few examples while not forgetting the base classes on…

Recent advancements in robot navigation, particularly with end-to-end learning approaches such as reinforcement learning (RL), have demonstrated strong performance. However, successful navigation still depends on two key capabilities:…

Few-shot instance segmentation methods are promising when labeled training data for novel classes is scarce. However, current approaches do not facilitate flexible addition of novel classes. They also require that examples of each class are…

Machine learning classifiers are often trained to recognize a set of pre-defined classes. However, in many applications, it is often desirable to have the flexibility of learning additional concepts, with limited data and without…

Few-shot class-incremental learning (FSCIL) is a paradigm where a model, initially trained on a dataset of base classes, must adapt to an expanding problem space by recognizing novel classes with limited data. We focus on the challenging…

Different from human nature, it is still common practice today for vision tasks to train deep learning models only initially and on fixed datasets. A variety of approaches have recently addressed handling continual data streams. However,…

Most meta-learning approaches assume the existence of a very large set of labeled data available for episodic meta-learning of base knowledge. This contrasts with the more realistic continual learning paradigm in which data arrives…

Cross-modal video-text retrieval, a challenging task in the field of vision and language, aims at retrieving corresponding instance giving sample from either modality. Existing approaches for this task all focus on how to design encoding…

For privacy and security concerns, the need to erase unwanted information from pre-trained vision models is becoming evident nowadays. In real-world scenarios, erasure requests originate at any time from both users and model owners, and…

Deep neural networks have enabled major progresses in semantic segmentation. However, even the most advanced neural architectures suffer from important limitations. First, they are vulnerable to catastrophic forgetting, i.e. they perform…

The ability to learn more and more concepts over time from incrementally arriving data is essential for the development of a life-long learning system. However, deep neural networks often suffer from forgetting previously learned concepts…