VASR: Visual Analogies of Situation Recognition

8 Dec 2022  ·  Yonatan Bitton, Ron Yosef, Eli Strugo, Dafna Shahaf, Roy Schwartz, Gabriel Stanovsky ·

A core process in human cognition is analogical mapping: the ability to identify a similar relational structure between different situations. We introduce a novel task, Visual Analogies of Situation Recognition, adapting the classical word-analogy task into the visual domain. Given a triplet of images, the task is to select an image candidate B' that completes the analogy (A to A' is like B to what?). Unlike previous work on visual analogy that focused on simple image transformations, we tackle complex analogies requiring understanding of scenes. We leverage situation recognition annotations and the CLIP model to generate a large set of 500k candidate analogies. Crowdsourced annotations for a sample of the data indicate that humans agree with the dataset label ~80% of the time (chance level 25%). Furthermore, we use human annotations to create a gold-standard dataset of 3,820 validated analogies. Our experiments demonstrate that state-of-the-art models do well when distractors are chosen randomly (~86%), but struggle with carefully chosen distractors (~53%, compared to 90% human accuracy). We hope our dataset will encourage the development of new analogy-making models. Website:

PDF Abstract


Introduced in the Paper:


Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Visual Reasoning VASR Swin 1:1 Accuracy 52.9 # 1
Visual Reasoning VASR ConvNeXt 1:1 Accuracy 51.2 # 2
Visual Reasoning VASR DEiT 1:1 Accuracy 47.2 # 4
Visual Reasoning VASR ViT 1:1 Accuracy 50.3 # 3