Open-World Object Detection (OWOD) is a challenging task that requires the detector to identify unlabeled objects and continuously demands the detector to learn new knowledge based on existing ones. Existing methods primarily focus on recalling unknown objects, neglecting to explore the reasons behind them. This paper aims to understand the model's behavior in predicting the unknown category.

Images taken between 2013 and 2015 are used as the validation set.

Semi-Supervised Domain Generalization (SSDG) aims to learn a model that is generalizable to an unseen target domain with only a few labels, and most existing SSDG methods assume that unlabeled training and testing samples are all known classes. However, a more realistic scenario is that known classes may be mixed with some unknown classes in unlabeled training and testing data.

However, how to evaluate model performance in this challenging task is still unsolved.

To meaningfully regularize the model's decision boundary, CODA introduces virtual unknown classes

Regularization terms, suchasL2 regularization leading toweightdecay,arecommonly employed during training to improve a model's generalization capabilities.