PLAID: Pyramid-Level Adaptive Imbalance-Aware Diversification for Source-Free Domain Adaptation in Power-Grid Temporal Action Detection
Temporal action detection (TAD) localizes safety-critical procedures in untrimmed power-grid operation videos. Cross-site changes in action duration and density create level-dependent feature collapse in temporal pyramids and noisy, incomplete pseudo-labels under source-free domain adaptation. We propose Pyramid-Level Adaptive Imbalance-Aware Diversification (PLAID), which augments Mean-Teacher self-training with pyramid-level representation regularization. Duration-Aware Sampling (DAS) first constructs token matrices at duration-matched pyramid levels. Cross-Level Borrowing (CLB) then supplies temporally aligned neighboring tokens to levels with limited pseudo-segment support, stabilizing the statistics used by subsequent constraints. Channel variance and decorrelation losses preserve feature diversity, while Rank-Gap Reweighting (RGR) scales these constraints according to each level’s effective-rank decline from its running maximum. Together, these label-free components reduce reliance on imperfect pseudo-labels without source videos or target annotations. On four controlled duration and density shifts in the Power Grid Operations benchmark, PLAID improves source-only ActionFormer by 2.5–6.0 mean average precision (mAP) points and outperforms Vanilla Mean-Teacher in every setting. With TemporalMaxer, it also surpasses both baselines at every evaluated temporal intersection-over-union (tIoU) threshold in two representative shifts. The results support pyramid-aware representation recovery as a practical strategy for adapting fixed-camera power-grid detectors across sites when operational tempo and action occupancy vary and source recordings cannot be shared.
Authors
- Mingyong Xin (ORCID: https://orcid.org/0000-0002-7521-6362)
- Xinshan Zhu (ORCID: https://orcid.org/0000-0003-2060-9932)
- Lingwen Meng (ORCID: https://orcid.org/0009-0003-0880-4927)
- Siwu Yu
Institutions
- Tianjin University (CN)
- Guizhou Power Grid Co., Ltd. (China) (CN)
Publication Details
- Journal
- Electronics
- Published
- 2026-11-18
- DOI
- https://doi.org/10.3390/electronics15225377
- Primary Topic
- Domain Adaptation and Few-Shot Learning
- Type
- article
- Field-Weighted Citation Impact
- 0.00