Incremental Learning Techniques for Semantic Segmentation
Deep learning architectures exhibit a critical drop of performance due to catastrophic forgetting when they are required to incrementally learn new tasks. Contemporary incremental learning frameworks focus on image classification and object detection while in this work we formally introduce the incremental learning problem for semantic segmentation in which a pixel-wise labeling is considered. To tackle this task we propose to distill the knowledge of the previous model to retain the information about previously learned classes, whilst updating the current model to learn the new ones. We propose various approaches working both on the output logits and on intermediate features. In opposition to some recent frameworks, we do not store any image from previously learned classes and only the last model is needed to preserve high accuracy on these classes. The experimental evaluation on the Pascal VOC2012 dataset shows the effectiveness of the proposed approaches.
Code (2)
Tasks
Disjoint 10-1Disjoint 15-1Disjoint 15-5Domain 1-1Domain 11-1Domain 11-5image-classificationImage ClassificationIncremental Learningobject-detectionObject DetectionOverlapped 100-5Overlapped 10-1Overlapped 15-1Overlapped 15-5SegmentationSemantic SegmentationSimilar Papers 제목 키워드 기반
A Contrastive Distillation Approach for Incremental Semantic Segmentation in Aerial Images
Incremental learning represents a crucial task in aerial image processing, especially given the limited availability of large-scale annotated datasets. A major issue concerning current deep neural architectures is known …
image-classificationImage ClassificationIncremental LearningKnowledge Distillation+4Semantic Image Segmentation: Two Decades of Research
Semantic image segmentation (SiS) plays a fundamental role in a broad variety of computer vision applications, providing key information for the global understanding of an image. This survey is an effort to summarize two…
Domain AdaptationDomain Generalizationimage-classificationImage Classification+11Towards Realistic Incremental Scenario in Class Incremental Semantic Segmentation
This paper addresses the unrealistic aspect of the commonly adopted Continuous Incremental Semantic Segmentation (CISS) scenario, termed overlapped. We point out that overlapped allows the same image to reappear in futur…
Class-Incremental Semantic SegmentationIncremental LearningSemantic SegmentationLearning with Style: Continual Semantic Segmentation Across Tasks and Domains
Deep learning models dealing with image understanding in real-world settings must be able to adapt to a wide variety of tasks across different domains. Domain adaptation and class incremental learning deal with domain an…
Autonomous Drivingclass-incremental learningClass Incremental LearningContinual Learning+5Continual 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+9