TAM: Task-Aware Memory Distillation for Efficient Spatiotemporal Prediction
Knowledge distillation enables efficient spatiotemporal prediction by transferring knowledge from an accurate teacher to a compact student. However, matching outputs or features independently for each sample leaves cross-sample predictive structure underused. Exploiting this structure requires representations and historical references that reflect the dynamics of each task. We propose TAM, a…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
Source: arxiv.org