Bitemporal remote sensing change detection requires representations that preserve spatial detail while capturing contextual information relevant to changes between acquisitions. Visual test-time training offers an alternative to explicit token-to-token attention by adapting a compact inner model to each image. This let...
Sharukshan Niranjan, Oshadha Samarakoon, N. Wasalathilaka et al.· 0 citations
Prompt sensitivity is widely treated as a model robustness deficiency. Yet the extent to which measured sensitivity reflects genuine model instability, rather than artifacts of the evaluation method used to measure it, remains largely underexplored. We introduce Evaluation-Attributable Sensitivity (EAS), a per-instance...
Sayumi Muthukumarana, Buddhi Wijenayake, R. Godaliyadda et al.· Moratuwa Engineering Researc...· 0 citations
This work decomposes multi-entity temporal dynamics into three interaction types: spatial interactions among entities, temporal interactions across time, and cross interactions coupling the two domains, and proposes a structured spatio-temporal transformer block that explicitly models all three within a single stage.