Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
retinaros
56 days ago
|
parent
|
context
|
favorite
| on:
Meta Segment Anything Model 3
yeah I tried too. Im trying a fine tuning on PIDs.
enoch2090
56 days ago
[–]
Looking forward to your progress! Just checked the paper and it says the underlying backbone is still DETR. My guess would be that SAM3 uses more video frames during the training process and caused the dilution of sparse engineering-paper-like data.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
