HIGHLIGHTS
- who: Vidit Vidit from the CVLab, EPFL, Rte Cantonale, Lausanne, Switzerland have published the paper: Attention-based domain adaptation for single-stage detectors, in the Journal: (JOURNAL)
- what: The authors demonstrate this on standard benchmark datasets by applying it to both the single-shot detector (SSD) and a recent variant of the You Only Look Once detector (YOLOv5). The authors focus on unsupervised domain adaptation, whose goal is to bridge the gap between the source (training) and target (test) domain without having access to any target annotations. In any event, in contrast to these approaches . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.