Methods › General › Attention Mechanisms › SEAM
Self-supervised Equivariant Attention Mechanism
SEAM
Introduced by Yude Wang et al. in Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentation
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Self-supervised Equivariant Attention Mechanism, or SEAM, is an attention mechanism for weakly supervised semantic segmentation. The SEAM applies consistency regularization on CAMs from various transformed images to provide self-supervision for network learning. To further improve the network prediction consistency, SEAM introduces the pixel correlation module (PCM), which captures context appearance information for each pixel and revises original CAMs by learned affinity attention maps. The SEAM is implemented by a siamese network with equivariant cross regularization (ECR) loss, which regularizes the original CAMs and the revised CAMs on different branches.
Papers archive 2025-07-28
14 shown of 14, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Self-Destructive Language Model 18 May 2025 · 0 repositories · arXiv:2505.12186Syntology ran 0 of 6 samples · 6 unverified
-
SEAM: A Stochastic Benchmark for Multi-Document Tasks 23 Jun 2024 · 0 repositories · arXiv:2406.16086
-
It Takes Two: On the Seamlessness between Reward and Policy Model in RLHF 12 Jun 2024 · 1 repository · arXiv:2406.07971Syntology ran 12 of 12 samples · 0 unverified · 12 pointer-only (licence)
-
CVFC: Attention-Based Cross-View Feature Consistency for Weakly Supervised Semantic Segmentation of Pathology Images 21 Aug 2023 · 0 repositories · arXiv:2308.10449
-
Joint Microseismic Event Detection and Location with a Detection Transformer 16 Jul 2023 · 0 repositories · arXiv:2307.09207
-
High-fidelity Pseudo-labels for Boosting Weakly-Supervised Segmentation 5 Apr 2023 · 1 repository · arXiv:2304.02621
-
ContrasInver: Ultra-Sparse Label Semi-supervised Regression for Multi-dimensional Seismic Inversion 13 Feb 2023 · 0 repositories · arXiv:2302.06441
-
Selective Amnesia: On Efficient, High-Fidelity and Blind Suppression of Backdoor Effects in Trojaned Machine Learning Models 9 Dec 2022 · 0 repositories · arXiv:2212.04687
-
Out-of-Candidate Rectification for Weakly Supervised Semantic Segmentation 22 Nov 2022 · 0 repositories · arXiv:2211.12268
-
CONSS: Contrastive Learning Approach for Semi-Supervised Seismic Facies Classification 10 Oct 2022 · 0 repositories · arXiv:2210.04776
-
YOLO-FaceV2: A Scale and Occlusion Aware Face Detector 3 Aug 2022 · 1 repository · arXiv:2208.02019
-
Semi-supervised Impedance Inversion by Bayesian Neural Network Based on 2-d CNN Pre-training 20 Nov 2021 · 1 repository · arXiv:2111.10596
-
MovingFashion: a Benchmark for the Video-to-Shop Challenge 6 Oct 2021 · 1 repository · arXiv:2110.02627
-
Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentation 9 Apr 2020 · 2 repositories · arXiv:2004.04581Syntology ran 3 of 3 samples · 0 unverified · 2 pointer-only (licence)
Tasks archive 2025-07-28
20 shown of 31 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
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