A semi-supervised framework with coarse-to-fine attention and dual-level memory detects fine-grained classes at close to fully supervised mAP using only coarse boxes and image labels.
Semi-supervised deep learning with memory
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Detecting 11K Classes: Large Scale Object Detection without Fine-Grained Bounding Boxes
A semi-supervised framework with coarse-to-fine attention and dual-level memory detects fine-grained classes at close to fully supervised mAP using only coarse boxes and image labels.