CARETS: A Consistency And Robustness Evaluative Test Suite for VQA

Abstract

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 changing the number of answer choices mentioned in the question. We release CARETS to be used as an extensible tool for evaluating multimodal model robustness. 1

Vision-Language Pre-training: Basics, Recent Advances, and Future Trends

“…VALSE (Parcalabescu et al, 2021) is proposed to test VLP models centered on linguistic phenomena. CARET (Jimenez et al, 2022) is proposed to systematically measure consistency and robustness of modern VQA models through six fine-grained capability tests.…”