Papers › Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled...

Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representations

10 Mar 2021CVPR 2021 1arXiv:2103.06342archive 2025-07-28

Umberto Michieli, Pietro Zanuttigh

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 categories are made available over time while previous training data is not retained. The proposed continual learning scheme shapes the latent space to reduce forgetting whilst improving the recognition of novel classes. Our framework is driven by three novel components which we also combine on top of existing techniques effortlessly. First, prototypes matching enforces latent space consistency on old classes, constraining the encoder to produce similar latent representation for previously seen classes in the subsequent steps. Second, features sparsification allows to make room in the latent space to accommodate novel classes. Finally, contrastive learning is employed to cluster features according to their semantics while tearing apart those of different classes. Extensive evaluation on the Pascal VOC2012 and ADE20K datasets demonstrates the effectiveness of our approach, significantly outperforming state-of-the-art methods.

PaperPDFConference PDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Continual LearningContinual Semantic SegmentationContrastive LearningDisjoint 10-1Disjoint 15-1Disjoint 15-5Overlapped 10-1Overlapped 15-1Overlapped 15-5Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Disjoint 10-1 PASCAL VOC 2012 SDR mIoU 14.3 #4 of 8 Archive leaderboard report
Disjoint 15-1 PASCAL VOC 2012 SDR mIoU 48.7 #5 of 9 Archive leaderboard report
Disjoint 15-5 PASCAL VOC 2012 SDR Mean IoU 67.3 #5 of 9 Archive leaderboard report
Overlapped 10-1 PASCAL VOC 2012 SDR mIoU 25.1 #10 of 13 Archive leaderboard report
Overlapped 15-1 PASCAL VOC 2012 SDR mIoU 39.5 #10 of 13 Archive leaderboard report
Overlapped 15-5 PASCAL VOC 2012 SDR Mean IoU (val) 70.1 #8 of 13 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Contrastive Learning

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections