A Competence-aware Curriculum for Visual Concepts Learning via Question Answering
This addresses the challenge of data efficiency and convergence speed in visual concept learning for AI systems, representing an incremental improvement over existing methods.
The paper tackles the problem of inefficient visual concept learning by proposing a competence-aware curriculum that mimics human progressive learning from easy to hard questions, achieving state-of-the-art performance on CLEVR with 40% less training data and three times faster convergence.
Humans can progressively learn visual concepts from easy to hard questions. To mimic this efficient learning ability, we propose a competence-aware curriculum for visual concept learning in a question-answering manner. Specifically, we design a neural-symbolic concept learner for learning the visual concepts and a multi-dimensional Item Response Theory (mIRT) model for guiding the learning process with an adaptive curriculum. The mIRT effectively estimates the concept difficulty and the model competence at each learning step from accumulated model responses. The estimated concept difficulty and model competence are further utilized to select the most profitable training samples. Experimental results on CLEVR show that with a competence-aware curriculum, the proposed method achieves state-of-the-art performances with superior data efficiency and convergence speed. Specifically, the proposed model only uses 40% of training data and converges three times faster compared with other state-of-the-art methods.