ruv
898aaef053
docs(adr-150): few-shot adaptation resolves the cross-subject frontier
Decisive result: 50 labeled frames/subject of in-room calibration ->
72.2% (reaches SOTA), 200 -> 76.1%, 1000 -> 78.3%. Few-shot target
adaptation dominates source volume (+24 subjects bought +6pt; 200 target
frames bought +12.4pt). Re-scopes the deployment story: ship a ~30s on-site
calibration, not a mass corpus. Foundation encoder's role shifts to making
that calibration cheaper. Supersedes the earlier data-bound pessimism.
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-05-31 01:47:00 -04:00
..
2026-05-31 01:47:00 -04:00
2026-05-17 18:18:07 -04:00
2026-05-31 01:30:29 -04:00
2026-05-12 23:15:10 +00:00
2026-05-25 22:47:48 -04:00
2026-04-25 21:28:13 -04:00
2026-05-11 23:40:55 -04:00
2026-05-24 13:00:38 -04:00
2026-05-12 23:15:10 +00:00
2026-04-25 23:07:52 -04:00
2026-05-23 16:13:28 -04:00
2026-05-24 20:20:25 -04:00
2026-05-25 22:47:48 -04:00
2026-05-17 17:41:39 -04:00
2026-05-23 15:34:48 -04:00
2026-05-23 15:34:48 -04:00
2026-04-25 23:07:52 -04:00
2026-04-29 19:34:24 -04:00
2026-05-29 08:46:12 -04:00
2026-04-25 21:28:13 -04:00
2026-05-17 18:01:44 -04:00
2026-05-25 17:36:40 -04:00
2026-05-29 19:50:21 -04:00
2026-04-25 21:28:13 -04:00
2026-05-28 18:57:08 -04:00
2026-05-23 15:34:48 -04:00