VILOD bundles t-SNE structure, uncertainty heatmaps, and model state views to let experts steer active learning for object detection; balanced visual guidance matched and slightly beat an automated AL baseline.
Title resolution pending
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
-
VILOD: A Visual Interactive Labeling Tool for Object Detection
VILOD bundles t-SNE structure, uncertainty heatmaps, and model state views to let experts steer active learning for object detection; balanced visual guidance matched and slightly beat an automated AL baseline.