Bongard-RWR+: Real-World Representations of Fine-Grained Concepts in Bongard Problems

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Pawlonka, Szymon, Małkiński, Mikołaj, Mańdziuk, Jacek
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910026323460096
author Pawlonka, Szymon
Małkiński, Mikołaj
Mańdziuk, Jacek
author_facet Pawlonka, Szymon
Małkiński, Mikołaj
Mańdziuk, Jacek
contents Bongard Problems (BPs) provide a challenging testbed for abstract visual reasoning (AVR), requiring models to identify visual concepts fromjust a few examples and describe them in natural language. Early BP benchmarks featured synthetic black-and-white drawings, which might not fully capture the complexity of real-world scenes. Subsequent BP datasets employed real-world images, albeit the represented concepts are identifiable from high-level image features, reducing the task complexity. Differently, the recently released Bongard-RWR dataset aimed at representing abstract concepts formulated in the original BPs using fine-grained real-world images. Its manual construction, however, limited the dataset size to just $60$ instances, constraining evaluation robustness. In this work, we introduce Bongard-RWR+, a BP dataset composed of $5\,400$ instances that represent original BP abstract concepts using real-world-like images generated via a vision language model (VLM) pipeline. Building on Bongard-RWR, we employ Pixtral-12B to describe manually curated images and generate new descriptions aligned with the underlying concepts, use Flux.1-dev to synthesize images from these descriptions, and manually verify that the generated images faithfully reflect the intended concepts. We evaluate state-of-the-art VLMs across diverse BP formulations, including binary and multiclass classification, as well as textual answer generation. Our findings reveal that while VLMs can recognize coarse-grained visual concepts, they consistently struggle with discerning fine-grained concepts, highlighting limitations in their reasoning capabilities.
format Preprint
id arxiv_https___arxiv_org_abs_2508_12026
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Bongard-RWR+: Real-World Representations of Fine-Grained Concepts in Bongard Problems
Pawlonka, Szymon
Małkiński, Mikołaj
Mańdziuk, Jacek
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Bongard Problems (BPs) provide a challenging testbed for abstract visual reasoning (AVR), requiring models to identify visual concepts fromjust a few examples and describe them in natural language. Early BP benchmarks featured synthetic black-and-white drawings, which might not fully capture the complexity of real-world scenes. Subsequent BP datasets employed real-world images, albeit the represented concepts are identifiable from high-level image features, reducing the task complexity. Differently, the recently released Bongard-RWR dataset aimed at representing abstract concepts formulated in the original BPs using fine-grained real-world images. Its manual construction, however, limited the dataset size to just $60$ instances, constraining evaluation robustness. In this work, we introduce Bongard-RWR+, a BP dataset composed of $5\,400$ instances that represent original BP abstract concepts using real-world-like images generated via a vision language model (VLM) pipeline. Building on Bongard-RWR, we employ Pixtral-12B to describe manually curated images and generate new descriptions aligned with the underlying concepts, use Flux.1-dev to synthesize images from these descriptions, and manually verify that the generated images faithfully reflect the intended concepts. We evaluate state-of-the-art VLMs across diverse BP formulations, including binary and multiclass classification, as well as textual answer generation. Our findings reveal that while VLMs can recognize coarse-grained visual concepts, they consistently struggle with discerning fine-grained concepts, highlighting limitations in their reasoning capabilities.
title Bongard-RWR+: Real-World Representations of Fine-Grained Concepts in Bongard Problems
topic Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2508.12026