<p>Vision Transformers have demonstrated strong performance across diverse visual tasks; however, their high computational cost due to long token sequences remains a critical challenge. Sequence reduction via pooling is a common strategy, yet relying on a single pooling operation often limits contextual representation. Motivated by the strong context abstraction capability of pyramid pooling, this work investigates its effective integration within a transformer-based framework for landslide detection from remote sensing imagery. Rather than introducing an entirely new backbone, we build upon the existing Pyramid Pooling Transformer and adapt it for landslide analysis by incorporating a multilayer pyramid pooling–based multi-head self-attention mechanism, enabling efficient sequence reduction while preserving multi-scale contextual information. This task-oriented adaptation allows the model to better capture the spatial heterogeneity and scale variability inherent in landslide scenes. Extensive experiments on a benchmark remote sensing landslide dataset demonstrate that the proposed PPT-based model significantly outperforms conventional CNNs and standard transformer baselines. Compared to state-of-the-art deep learning models, the proposed approach achieves improvements of 7.3% in F1-score and 2% in overall accuracy, highlighting the effectiveness of pyramid pooling–driven attention mechanisms for landslide detection.</p>