3 papers
cs.RO2020
On the Guaranteed Almost Equivalence between Imitation Learning from Observation and Demonstration
Zhihao Cheng, Liu Liu, Aishan Liu +3
Imitation learning from observation (LfO) is more preferable than imitation learning from demonstration (LfD) due to the nonnecessity of expert actions when reconstructing the expe…
cs.CV2019
Revisiting Metric Learning for Few-Shot Image Classification
Xiaomeng Li, Lequan Yu, Chi-Wing Fu +2
The goal of few-shot learning is to recognize new visual concepts with just a few amount of labeled samples in each class. Recent effective metric-based few-shot approaches employ…
stat.ML2018
Towards Query Efficient Black-box Attacks: An Input-free Perspective
Yali Du, Meng Fang, Jinfeng Yi +2
Recent studies have highlighted that deep neural networks (DNNs) are vulnerable to adversarial attacks, even in a black-box scenario. However, most of the existing black-box attack…