ODIS replaces image-level self-distillation with object-level distillation using segmentation-guided cropping and masked attention, improving image- and patch-level benchmarks over iBOT.
Towards in-context scene understanding
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Object-level Self-Distillation for Vision Pretraining
ODIS replaces image-level self-distillation with object-level distillation using segmentation-guided cropping and masked attention, improving image- and patch-level benchmarks over iBOT.