Self-Training for Class-Incremental Semantic Segmentation
In class-incremental semantic segmentation, we have no access to the labeled data of previous tasks. Therefore, when incrementally learning new classes, deep neural networks suffer from catastrophic forgetting of previously learned knowledge. To address this problem, we propose to apply a self-training approach that leverages unlabeled data, which is used for the rehearsal of previous knowledge. Specifically, we first learn a temporary model for the current task, and then pseudo labels for the unlabeled data are computed by fusing information from the old model of the previous task and the current temporary model. Additionally, conflict reduction is proposed to resolve the conflicts of pseudo labels generated from both the old and temporary models. We show that maximizing self-entropy can further improve results by smoothing the overconfident predictions. Interestingly, in the experiments we show that the auxiliary data can be different from the training data and that even general-purpose but diverse auxiliary data can lead to large performance gains. The experiments demonstrate state-of-the-art results: obtaining a relative gain of up to 114% on Pascal-VOC 2012 and 8.5% on the more challenging ADE20K compared to previous state-of-the-art methods.
Code (0)
등록된 구현이 없습니다.
Tasks
Class-Incremental Semantic SegmentationIncremental LearningSemantic SegmentationSimilar Papers 제목 키워드 기반
End-to-End 3D-PointCloud Semantic Segmentation for Autonomous Driving
3D semantic scene labeling is a fundamental task for Autonomous Driving. Recent work shows the capability of Deep Neural Networks in labeling 3D point sets provided by sensors like LiDAR, and Radar. Imbalanced distributi…
Autonomous DrivingScene LabelingSemantic SegmentationTransfer LearningContinual Learning for LiDAR Semantic Segmentation: Class-Incremental and Coarse-to-Fine strategies on Sparse Data
During the last few years, continual learning (CL) strategies for image classification and segmentation have been widely investigated designing innovative solutions to tackle catastrophic forgetting, like knowledge disti…
class-incremental learningClass Incremental LearningContinual Learningimage-classification+6Prototype-based Incremental Few-Shot Semantic Segmentation
Semantic segmentation models have two fundamental weaknesses: i) they require large training sets with costly pixel-level annotations, and ii) they have a static output space, constrained to the classes of the training s…
Few-Shot Semantic SegmentationIncremental LearningKnowledge DistillationSegmentation+1Continual Learning for Class- and Domain-Incremental Semantic Segmentation
The field of continual deep learning is an emerging field and a lot of progress has been made. However, concurrently most of the approaches are only tested on the task of image classification, which is not relevant in th…
class-incremental learningClass Incremental LearningClass-Incremental Semantic SegmentationContinual Learning+9An EM Framework for Online Incremental Learning of Semantic Segmentation
Incremental learning of semantic segmentation has emerged as a promising strategy for visual scene interpretation in the open- world setting. However, it remains challenging to acquire novel classes in an online fashion …
Incremental LearningMissing LabelsSegmentationSemantic Segmentation