Recomposición dinámica bidireccional de datos para la segmentación eficiente de basura en carreteras en aprendizaje...

Deep neural networks excel in road garbage segmentation but require costly pixel-level annotations. Balancing accuracy and annotation costs is a key bottleneck in urban garbage management. Semi-supervised learning (SSL) reduces the dependence on annotations by utilizing large amounts of unlabeled data. However, existing methods face a key challenge: under extreme annotation imbalance, the scarce labeled data often lacks diversity. This leads to repeated reuse during training, preventing full information exploitation and causing model performance stagnation. Specifically, we introduce the Dynamic Bidirectional Data Recomposition (DBDR) mechanism, which dynamically adjusts the bidirectional information interaction between labeled and unlabeled data to solve the problem of representation stagnation. Early training: The labeled data is integrated into the unlabeled data stream according to confidence levels, guiding the model to prioritize capturing and stabilizing basic semantic prototypes. Mid-training: A dynamic memory queue is constructed to quantify the evolution of model confidence states over time. We use dynamic thresholds and dual validation to trigger a reverse flow of knowledge from unlabeled to labeled supervision. This breaks local optima in the encoder and reshapes the semantic decision boundaries. DBDR can be integrated into any current mainstream SSL framework. On a real-world road garbage dataset, DBDR delivers a significant performance boost over all five state-of-the-art baseline models. Ablation experiments validate its key improvements in the segmentation of confusing targets (e.g., plastic, paper). This research provides an economically feasible solution for future smart city waste management technologies.