Learning task-agnostic representation via toddler-inspired learning
This addresses the limitation of passive learning in AI for researchers in computer vision and robotics, though it is incremental as it builds on existing interactive learning concepts.
The paper tackles the problem of AI systems' reliance on labeled data by designing an interactive agent inspired by toddler learning to acquire task-agnostic visual representations through environmental interaction. The model achieved accuracies of 100% and 75.1% and a relative error of 1.62% on tasks like image classification and object localization, outperforming autoencoder-based models and being comparable to supervised models.
One of the inherent limitations of current AI systems, stemming from the passive learning mechanisms (e.g., supervised learning), is that they perform well on labeled datasets but cannot deduce knowledge on their own. To tackle this problem, we derive inspiration from a highly intentional learning system via action: the toddler. Inspired by the toddler's learning procedure, we design an interactive agent that can learn and store task-agnostic visual representation while exploring and interacting with objects in the virtual environment. Experimental results show that such obtained representation was expandable to various vision tasks such as image classification, object localization, and distance estimation tasks. In specific, the proposed model achieved 100%, 75.1% accuracy and 1.62% relative error, respectively, which is noticeably better than autoencoder-based model (99.7%, 66.1%, 1.95%), and also comparable with those of supervised models (100%, 87.3%, 0.71%).