Visual Superordinate Abstraction for Robust Concept Learning

Abstract

Concept learning constructs visual representations that are connected to linguistic semantics, which is fundamental to vision-language tasks. Although promising progress has been made, existing concept learners are still vulnerable to attribute perturbations and out-of-distribution compositions during inference. We ascribe the bottleneck to a failure of exploring the intrinsic semantic hierarchy of visual concepts, e.g. \{red, blue,...\} $\in$ `color' subspace yet cube $\in$ `shape'. In this paper, we propose a visual superordinate abstraction framework for explicitly modeling semantic-aware visual subspaces (i.e. visual superordinates). With only natural visual question answering data, our model first acquires the semantic hierarchy from a linguistic view, and then explores mutually exclusive visual superordinates under the guidance of linguistic hierarchy. In addition, a quasi-center visual concept clustering and a superordinate shortcut learning schemes are proposed to enhance the discrimination and independence of concepts within each visual superordinate. Experiments demonstrate the superiority of the proposed framework under diverse settings, which increases the overall answering accuracy relatively by 7.5\% on reasoning with perturbations and 15.6\% on compositional generalization tests.

arXiv comment14 pages, 11 figures

References in corpus (7)

• Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding
• Transparency by Design: Closing the Gap Between Performance and Interpretability in Visual Reasoning
• The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision
• Compositional Attention Networks for Machine Reasoning
• Deconfounded Image Captioning: A Causal Retrospect
• Causal Induction from Visual Observations for Goal Directed Tasks
• Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning