Multi-Scale Attention
Overview
Multi-scale attention studies how models can combine fine-grained features with broader context across image regions, feature-pyramid levels, or time windows. Common approaches include hierarchical and window-based attention, cross-scale feature fusion, and efficient linear attention that allocates computation across resolutions. These methods are used in tasks such as object detection and segmentation on benchmarks like COCO and ADE20K, as well as time-series forecasting and sequence modeling. A central challenge is aligning useful information across scales while controlling computation, and gains must be tested across varied datasets and settings.
Latest papers
39 papers7 papers in the last four weeks, up 133% on the four weeks before. 0.0% of all new papers.