SRI International
-
DUDA: Distilled unsupervised domain adaptation for lightweight semantic segmentation
Abstract Unsupervised Domain Adaptation (UDA) is essential for enabling semantic segmentation in new domains without requiring costly pixel-wise annotations. State-of-the-art (SOTA) UDA methods primarily use self-training with architecturally identical teacher and student networks, relying on Exponential Moving Average (EMA) updates. However, these approaches face substantial performance degradation with lightweight models due to inherent architectural inflexibility…
-

Case study: How SRI’s spinout of LeoLabs launched a revolution in low earth orbit intelligence
By pursuing a new application for its proven radar technology, SRI transformed its orbital intelligence capabilities into a startup that’s securing both commercial and defense-related space missions.
-

PARC Forum: Future of quantum as it moves from lab to fab
How can we scale quantum technologies into real-world applications? Join us at SRI’s PARC Forum as we bring together leading voices across the quantum value chain to explore how to scale quantum technologies into real-world applications. Featuring speakers from GlobalFoundries and the SRI-managed QED-C, discussions will cover the state of the quantum ecosystem, manufacturing at…








