CARETS: A Consistency And Robustness Evaluative Test Suite for VQA
This provides a systematic tool for evaluating multi-modal model robustness, addressing a domain-specific need in VQA research, though it is incremental as it builds on existing test sets.
The authors tackled the problem of evaluating consistency and robustness in Visual Question Answering (VQA) models by introducing CARETS, a test suite with six fine-grained capability tests, and found that even sophisticated models show weaknesses in handling concepts like negation and logical symmetry.
We introduce CARETS, a systematic test suite to measure consistency and robustness of modern VQA models through a series of six fine-grained capability tests. In contrast to existing VQA test sets, CARETS features balanced question generation to create pairs of instances to test models, with each pair focusing on a specific capability such as rephrasing, logical symmetry or image obfuscation. We evaluate six modern VQA systems on CARETS and identify several actionable weaknesses in model comprehension, especially with concepts such as negation, disjunction, or hypernym invariance. Interestingly, even the most sophisticated models are sensitive to aspects such as swapping the order of terms in a conjunction or varying the number of answer choices mentioned in the question. We release CARETS to be used as an extensible tool for evaluating multi-modal model robustness.