PLAID: Pyramid-Level Adaptive Imbalance-Aware Diversification for Source-Free Domain Adaptation in Power-Grid Temporal Action Detection
Year: 2026
Type: article
Abstract: 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.
Source: Electronics
Authors: Lingwen Meng(Conceptualization, Formal analysis, Funding acquisition, Investigation, Methodology, Project administration, Software, Supervision, Validation, Visualization, Writing – original draft, Writing – review & editing), Siwu Yu(Data curation, Formal analysis, Investigation, Resources, Software, Validation, Visualization, Writing – original draft, Writing – review & editing), Mingyong Xin(Data curation, Formal analysis, Investigation, Resources, Software, Validation, Visualization, Writing – review & editing), Xinshan Zhu(Conceptualization, Formal analysis, Funding acquisition, Methodology, Project administration, Supervision, Validation, Writing – review & editing)
Institutions: Guizhou Power Grid Co., Ltd. (China), Tianjin University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $2,896
OpenAlex ID: W7235852162
