2 papers
cs.CV2019
Prediction stability as a criterion in active learning
Junyu Liu, Xiang Li, Jin Wang +2
Recent breakthroughs made by deep learning rely heavily on large number of annotated samples. To overcome this shortcoming, active learning is a possible solution. Beside the previ…
cs.CV2018
PartsNet: A Unified Deep Network for Automotive Engine Precision Parts Defect Detection
Zhenshen Qu, Jianxiong Shen, Ruikun Li +2
Defect detection is a basic and essential task in automatic parts production, especially for automotive engine precision parts. In this paper, we propose a new idea to construct a…