Related papers: Representation Compensation Networks for Continual…

Continual learning (CL) aims to incrementally learn different tasks (such as classification) in a non-stationary data stream without forgetting old ones. Most CL works focus on tackling catastrophic forgetting under a learning-from-scratch…

We introduce CellSegmenter, a structured deep generative model and an amortized inference framework for unsupervised representation learning and instance segmentation tasks. The proposed inference algorithm is convolutional and…

In this paper, we work on a sound recognition system that continually incorporates new sound classes. Our main goal is to develop a framework where the model can be updated without relying on labeled data. For this purpose, we propose…

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…

Real-world natural language processing (NLP) models need to be continually updated to fix the prediction errors in out-of-distribution (OOD) data streams while overcoming catastrophic forgetting. However, existing continual learning (CL)…

Recent efforts in multi-domain learning for semantic segmentation attempt to learn multiple geographical datasets in a universal, joint model. A simple fine-tuning experiment performed sequentially on three popular road scene segmentation…

Capturing global contextual representations by exploiting long-range pixel-pixel dependencies has shown to improve semantic segmentation performance. However, how to do this efficiently is an open question as current approaches of utilising…

Continual Reinforcement Learning (CRL) aims to develop lifelong learning agents to continuously acquire knowledge across diverse tasks while mitigating catastrophic forgetting. This requires efficiently managing the stability-plasticity…

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…

Textual information is considered as significant supplement to knowledge representation learning (KRL). There are two main challenges for constructing knowledge representations from plain texts: (1) How to take full advantages of sequential…

Evolving data streams induce joint nonstationarity in continual semantic segmentation, where semantic classes, input distributions, and supervision availability change simultaneously over time. This setting reflects practical structured…

Continual learning, involving sequential training on diverse tasks, often faces catastrophic forgetting. While knowledge distillation-based approaches exhibit notable success in preventing forgetting, we pinpoint a limitation in their…

Lifelong learning, the problem of continual learning where tasks arrive in sequence, has been lately attracting more attention in the computer vision community. The aim of lifelong learning is to develop a system that can learn new tasks…

This work addresses the task of open world semantic segmentation using RGBD sensing to discover new semantic classes over time. Although there are many types of objects in the real-word, current semantic segmentation methods make a closed…

Latent representation learned from multi-layered neural networks via hierarchical feature abstraction enables recent success of deep learning. Under the deep learning framework, generalization performance highly depends on the learned…

Humans learn adaptively and efficiently throughout their lives. However, incrementally learning tasks causes artificial neural networks to overwrite relevant information learned about older tasks, resulting in 'Catastrophic Forgetting'.…

Class-incremental semantic segmentation (CISS) labels each pixel of an image with a corresponding object/stuff class continually. To this end, it is crucial to learn novel classes incrementally without forgetting previously learned…

Accurate retinal vessel segmentation is an important task for many computer-aided diagnosis systems. Yet, it is still a challenging problem due to the complex vessel structures of an eye. Numerous vessel segmentation methods have been…

Deep learning approaches to 3D shape segmentation are typically formulated as a multi-class labeling problem. Existing models are trained for a fixed set of labels, which greatly limits their flexibility and adaptivity. We opt for top-down…

Modeling crisp logical regularities is crucial in semantic parsing, making it difficult for neural models with no task-specific prior knowledge to achieve good results. In this paper, we introduce data recombination, a novel framework for…