Pixels to Tokens: Token Space Efficient Active Learning for Low-Budget Semantic Segmentation
Imported from official source
While foundation models and vision transformers (ViTs) have redefined visual representations, current active learning (AL) strategies for these backbones largely operate at the patch or region level, where annotation requirements remain high due to extensive pixel labeling. …
This version
- Version
- 1 of 1
- Recorded
- November 10, 2026 23:01
- Change
- Initial
- Content hash
0db53560a16ae425a99ae2e3b8ccfad0- All versions
- Revision history