Language-Conditioned Graph Networks for Relational Reasoning

Solving grounded language tasks often requires reasoning about relationships between objects in the context of a given task. For example, to answer the question "What color is the mug on the plate?" we must check the color of the specific mug that satisfies the "on" relationship with respect to the plate. Recent work has proposed various methods capable of complex relational reasoning. However, most of their power is in the inference structure, while the scene is represented with simple local appearance features. In this paper, we take an alternate approach and build contextualized representations for objects in a visual scene to support relational reasoning. We propose a general framework of Language-Conditioned Graph Networks (LCGN), where each node represents an object, and is described by a context-aware representation from related objects through iterative message passing conditioned on the textual input. E.g., conditioning on the "on" relationship to the plate, the object "mug" gathers messages from the object "plate" to update its representation to "mug on the plate", which can be easily consumed by a simple classifier for answer prediction. We experimentally show that our LCGN approach effectively supports relational reasoning and improves performance across several tasks and datasets. Our code is available at http://ronghanghu.com/lcgn.

PDF Abstract ICCV 2019 PDF ICCV 2019 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Visual Question Answering (VQA) CLEVR single-hop + LCGN (ours) Accuracy 97.9 # 9
Referring Expression Comprehension CLEVR-Ref+ GroundeR + LCGN (ours) Accuracy 74.8 # 3
Visual Question Answering (VQA) GQA test-dev single-hop + LCGN (ours) Accuracy 55.8 # 8
Visual Question Answering (VQA) GQA test-std single-hop + LCGN (ours) Accuracy 56.1 # 5

Methods


No methods listed for this paper. Add relevant methods here