Papers › Illusory VQA: Benchmarking and Enhancing Multimodal Models on Visual Illusions

Illusory VQA: Benchmarking and Enhancing Multimodal Models on Visual Illusions

11 Dec 2024arXiv:2412.08169archive 2025-07-28

Mohammadmostafa Rostamkhani, Baktash Ansari, Hoorieh Sabzevari, Farzan Rahmani, Sauleh Eetemadi

In recent years, Visual Question Answering (VQA) has made significant strides, particularly with the advent of multimodal models that integrate vision and language understanding. However, existing VQA datasets often overlook the complexities introduced by image illusions, which pose unique challenges for both human perception and model interpretation. In this study, we introduce a novel task called Illusory VQA, along with four specialized datasets: IllusionMNIST, IllusionFashionMNIST, IllusionAnimals, and IllusionChar. These datasets are designed to evaluate the performance of state-of-the-art multimodal models in recognizing and interpreting visual illusions. We assess the zero-shot performance of various models, fine-tune selected models on our datasets, and propose a simple yet effective solution for illusion detection using Gaussian and blur low-pass filters. We show that this method increases the performance of models significantly and in the case of BLIP-2 on IllusionAnimals without any fine-tuning, it outperforms humans. Our findings highlight the disparity between human and model perception of illusions and demonstrate that fine-tuning and specific preprocessing techniques can significantly enhance model robustness. This work contributes to the development of more human-like visual understanding in multimodal models and suggests future directions for adapting filters using learnable parameters.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

IllusoryVQA/IllusoryVQA officialmentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

BenchmarkingQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)

Datasets

Introduced by this paper, per the archive.

IllusionAnimals_testIllusionChar_testIllusionFashionMNIST_testIllusionMNIST_test

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections