Disjoint 15-5
1개 벤치마크 · 논문 8편 · 이 태스크의 논문 보기 →
Benchmarks
PASCAL VOC 2012
Most implemented
Learning without Forgetting
PLOP: Learning without Forgetting for Continual Semantic Segmentation
Incremental Learning Techniques for Semantic Segmentation
Mitigating Background Shift in Class-Incremental Semantic Segmentation
Representation Compensation Networks for Continual Semantic Segmentation
Papers
Mitigating Background Shift in Class-Incremental Semantic Segmentation
Class-Incremental Semantic Segmentation(CISS) aims to learn new classes without forgetting the old ones, using only the labels of the new classes. To achieve this, two popular strategies are employed: 1) pseudo-labeling …
Class Incremental LearningClass-Incremental Semantic SegmentationContinual LearningContinual Semantic Segmentation+15Representation Compensation Networks for Continual Semantic Segmentation
In this work, we study the continual semantic segmentation problem, where the deep neural networks are required to incorporate new classes continually without catastrophic forgetting. We propose to use a structural re-pa…
Class Incremental LearningContinual LearningContinual Semantic SegmentationDisjoint 10-1+15SSUL: Semantic Segmentation with Unknown Label for Exemplar-based Class-Incremental Learning
This paper introduces a solid state-of-the-art baseline for a class-incremental semantic segmentation (CISS) problem. While the recent CISS algorithms utilize variants of the knowledge distillation (KD) technique to tack…
class-incremental learningClass Incremental LearningClass-Incremental Semantic SegmentationContinual Semantic Segmentation+14Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representations
Deep neural networks suffer from the major limitation of catastrophic forgetting old tasks when learning new ones. In this paper we focus on class incremental continual learning in semantic segmentation, where new catego…
Continual LearningContinual Semantic SegmentationContrastive LearningDisjoint 10-1+6PLOP: Learning without Forgetting for Continual Semantic Segmentation
Deep learning approaches are nowadays ubiquitously used to tackle computer vision tasks such as semantic segmentation, requiring large datasets and substantial computational power. Continual learning for semantic segment…
Class Incremental LearningContinual LearningContinual Semantic SegmentationDisjoint 10-1+15Modeling the Background for Incremental Learning in Semantic Segmentation
Despite their effectiveness in a wide range of tasks, deep architectures suffer from some important limitations. In particular, they are vulnerable to catastrophic forgetting, i.e. they perform poorly when they are requi…
Continual LearningDisjoint 10-1Disjoint 15-1Disjoint 15-5+8