Class-Incremental Learning is a challenging problem in machine learning that aims to extend previously trained neural networks with new classes. This especially useful if the system able classify objects despite original training data being unavailable. Although semantic segmentation has received less attention than classification, it poses distinct problems and challenges, since previous futur...

Incremental systems often suffer from ordering effects: the knowledge structures that they form may vary with the presentation of objects. We discuss this phenomenon primarily in the context of an incremental, unsupervised system known as COBWEB, but speculate of related phenomena found in supervised systems such as ID4.

Within a statistical learning setting, we propose and study an iterative regularization algorithm for least squares defined by an incremental gradient method. In particular, we show that, if all other parameters are fixed a priori, the number of passes over the data (epochs) acts as a regularization parameter, and prove strong universal consistency, i.e. almost sure convergence of the risk, as ...

Given an existing trained neural network, it is often desirable to be able to add new capabilities without hindering performance of already learned tasks. Existing approaches either learn sub-optimal solutions, require joint training, or incur a substantial increment in the number of parameters for each added task, typically as many as the original network. We propose a method which fully prese...

Incremental learning of visual categories denotes the capability of a visual perceptual system to build up an increasing repertoire of visual concepts based on a sequence of experiences. A visual category is here defined as a possibly large group of individual objects that share similar properties like shape, appearance, or color. Biological visual systems achieve this function very efficiently...

We present a biologically motivated architecture for object recognition that is based on a hierarchical feature-detection model in combination with a memory architecture that implements short-term and long-term memory for objects. A particular focus is the functional realization of online and incremental learning for the task of appearance-based object recognition of many complex-shaped objects...