paper-with-me

Papers

Mitigating Background Shift in Class-Incremental Semantic Segmentation

2024-07-16 · Gilhan Park, WonJun Moon, SuBeen Lee, Tae-Young Kim, Jae-Pil Heo

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 and knowledge distillation to preserve prior knowledge; and 2) background weight transfer, which leverages the broad coverage of background in learning new classes by transferring background weight to the new class classifier. However, the first strategy heavily relies on the old model in detecting old classes while undetected pixels are regarded as the background, thereby leading to the background shift towards the old classes(i.e., misclassification of old class as background). Additionally, in the case of the second approach, initializing the new class classifier with background knowledge triggers a similar background shift issue, but towards the new classes. To address these issues, we propose a background-class separation framework for CISS. To begin with, selective pseudo-labeling and adaptive feature distillation are to distill only trustworthy past knowledge. On the other hand, we encourage the separation between the background and new classes with a novel orthogonal objective along with label-guided output distillation. Our state-of-the-art results validate the effectiveness of these proposed methods.

📄 PDF Abstract BibTeX arXiv:2407.11859

Code (1)

roadonep/eccv2024_mbs 공식 구현 pytorch

Tasks

Class Incremental LearningClass-Incremental Semantic SegmentationContinual LearningContinual Semantic SegmentationDisjoint 15-1Disjoint 15-5Disjoint 19-1Knowledge DistillationOverlapped 100-10Overlapped 100-5Overlapped 100-50Overlapped 10-1Overlapped 15-1Overlapped 15-5Overlapped 19-1Overlapped 50-50Overlapped 5-3SegmentationSemantic Segmentation

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

Attribution-aware Weight Transfer: A Warm-Start Initialization for Class-Incremental Semantic Segmentation

2022-10-13 · Dipam Goswami, René Schuster, Joost Van de Weijer, Didier Stricker

In class-incremental semantic segmentation (CISS), deep learning architectures suffer from the critical problems of catastrophic forgetting and semantic background shift. Although recent works focused on these issues, ex…

Class-Incremental Semantic SegmentationContinual LearningOverlapped 100-10Overlapped 100-5+8

Background Adaptation with Residual Modeling for Exemplar-Free Class-Incremental Semantic Segmentation

2024-07-13 · Anqi Zhang, Guangyu Gao

Class Incremental Semantic Segmentation~(CISS), within Incremental Learning for semantic segmentation, targets segmenting new categories while reducing the catastrophic forgetting on the old categories.Besides, backgroun…

Class-Incremental Semantic SegmentationExemplar-FreeIncremental LearningKnowledge Distillation+2

Causes of Catastrophic Forgetting in Class-Incremental Semantic Segmentation

2022-09-16 · Tobias Kalb, Jürgen Beyerer

Class-incremental learning for semantic segmentation (CiSS) is presently a highly researched field which aims at updating a semantic segmentation model by sequentially learning new semantic classes. A major challenge in …

class-incremental learningClass Incremental LearningClass-Incremental Semantic SegmentationIncremental Learning+3

Modeling the Background for Incremental Learning in Semantic Segmentation

2020-02-03 · CVPR 2020 6 · Fabio Cermelli, Massimiliano Mancini, Samuel Rota Bulò, Elisa Ricci 외

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

Gradient-Semantic Compensation for Incremental Semantic Segmentation

2023-07-20 · Wei Cong, Yang Cong, Jiahua Dong, Gan Sun 외

Incremental semantic segmentation aims to continually learn the segmentation of new coming classes without accessing the training data of previously learned classes. However, most current methods fail to address catastro…

SegmentationSemantic Segmentation