By distilling a large teacher into a MobileNetV2 student and adding a reinforcement-learned canvas selector, the authors reduce FG-SBIR compute from 40.18G to 0.254G FLOPs with accuracy 32.77% vs 33.03%.
Sketch less for more: On-the-fly fine-grained sketch based image retrieval
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Sketch Down the FLOPs: Towards Efficient Networks for Human Sketch
By distilling a large teacher into a MobileNetV2 student and adding a reinforcement-learned canvas selector, the authors reduce FG-SBIR compute from 40.18G to 0.254G FLOPs with accuracy 32.77% vs 33.03%.