Introduced in CLEVR-Ref+: Diagnosing Visual Reasoning with Referring Expressions
CLEVR-Ref+ is a synthetic diagnostic dataset for referring expression comprehension. The precise locations and attributes of the objects are readily available, and the referring expressions are automatically associated with functional programs. The synthetic nature allows control over dataset bias (through sampling strategy), and the modular programs enable intermediate reasoning ground truth without human annotators.
Source: CLEVR-Ref+: Diagnosing Visual Reasoning with Referring Expressions
Unknown
