research
∙
10/30/2021
Three approaches to facilitate DNN generalization to objects in out-of-distribution orientations and illuminations: late-stopping, tuning batch normalization and invariance los
The training data distribution is often biased towards objects in certai...
share
research
∙
10/03/2021
Annotation Cost Reduction of Stream-based Active Learning by Automated Weak Labeling using a Robot Arm
Stream-based active learning (AL) is an efficient training data collecti...
research
∙
12/22/2020
Selective Forgetting of Deep Networks at a Finer Level than Samples
Selective forgetting or removing information from deep neural networks (...
research
∙
12/17/2018