Low-Shot Learning from Imaginary Data

• Published in: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 7278 - 7286
• Main Authors: Wang, Yu-Xiong, Girshick, Ross, Hebert, Martial, Hariharan, Bharath
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2018
• Subjects: Data visualization; Feature extraction; Machine vision; Strain; Task analysis; Training; Visualization

Humans can quickly learn new visual concepts, perhaps because they can easily visualize or imagine what novel objects look like from different views. Incorporating this ability to hallucinate novel instances of new concepts might help machine vision systems perform better low-shot learning, i.e., le...