Active Object Manipulation Facilitates Visual Object Learning: An Egocentric Vision Study
This work addresses how infants efficiently learn object recognition with minimal data, though it is incremental as a follow-up study.
The study investigated whether active object manipulation by children improves visual object learning in few-shot scenarios, finding that supervision with hand manipulation consistently outperforms learning without hands.
Inspired by the remarkable ability of the infant visual learning system, a recent study collected first-person images from children to analyze the `training data' that they receive. We conduct a follow-up study that investigates two additional directions. First, given that infants can quickly learn to recognize a new object without much supervision (i.e. few-shot learning), we limit the number of training images. Second, we investigate how children control the supervision signals they receive during learning based on hand manipulation of objects. Our experimental results suggest that supervision with hand manipulation is better than without hands, and the trend is consistent even when a small number of images is available.