Incremental Learning with Unlabeled Data in the Wild

7 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Incremental Few-Shot Semantic Segmentation via Embedding Adaptive-Update and Hyper-class Representation (2022, background): “Since it’s not capable to properly distinguish between old and new classes, later approaches [2, 19] utilize the memory of old classes for further training by considering distribution relationship between base and new classes.”
Three scenarios for continual learning (2019, methodology): “This categorization scheme was first introduced in a previous paper by us [10] and has since been adopted by several other studies [11, 12, 13]; the purpose of the current report is to provide a more in-depth treatment.”
Class-Incremental Learning for Semantic Segmentation Re-Using Neither Old Data Nor Old Labels (2020, methodology): “For this, we implemented two approaches from image classification [12], [13], adopting them to semantic segmentation (see Sections III-D, LWOF, and III-E, LWM) and also one approach from semantic segmentation [15] in our setting (Section III-F, Michieli).”
Relationship Matters: Relation Guided Knowledge Transfer for Incremental Learning of Object Detectors (2020, background): “Another is class-incremental learning where the number of class labels keeps growing [30, 6, 19, 2].”