Deep networks have shown remarkable results in the task of object detection. However, their performance suffers critical drops when they are subsequently trained on novel classes without any sample from the base classes originally used to train the model. This phenomenon is known as catastrophic forgetting. Recently, several incremental learning methods are proposed to mitigate catastrophic forgetting for object detection. Despite the effectiveness, these methods require co-occurrence of the unlabeled base classes in the training data of the novelclasses. This requirement isimpractical in manyreal-world settings since the base classes do not necessarily co-occur with the novel classes.

Sequential recommendation aims to recommend the next item that matches a user's

We demonstrate the efficiency of our protocol for distributed optimization with strongtheoreticalguarantees.

Large language models (LLMs) have shown impressive performance on downstream tasks by in-contextlearning (ICL), which heavily relies on the quality of demonstrations selected from a large set of annotated examples.

We consider both exact andapproximate recoveryofthelabels. Our results hold for anyconstant-factor approximation tothek-means problem.