# Are Elephants Bigger than Butterflies? Reasoning about Sizes of Objects

arXiv: https://arxiv.org/abs/1602.00753 · HTML: https://mlsanity.com/paper/1602.00753/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Feb 2016.

## Built on by (most cited first, 22 of 22)

- [Language Is Not All You Need: Aligning Perception with Language Models](https://mlsanity.com/paper/2302.14045/) (2023)
- [Things not Written in Text: Exploring Spatial Commonsense from Visual Signals](https://mlsanity.com/paper/2203.08075/) (2022)
- [Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd Schema](https://mlsanity.com/paper/2104.08161/) (2021)
- [Learning Visual Representations via Language-Guided Sampling](https://mlsanity.com/paper/2302.12248/) (2023)
- [Lumen: Unleashing Versatile Vision-Centric Capabilities of Large Multimodal Models](https://mlsanity.com/paper/2403.07304/) (2024)
- [SpaCE-10: A Comprehensive Benchmark for Multimodal Large Language Models in Compositional Spatial Intelligence](https://mlsanity.com/paper/2506.07966/) (2025)
- [Mitigating Temporal Misalignment by Discarding Outdated Facts](https://mlsanity.com/paper/2305.14824/) (2023)
- [Visually-Augmented Language Modeling](https://mlsanity.com/paper/2205.10178/) (2022)
- [Did the Cat Drink the Coffee? Challenging Transformers with Generalized Event Knowledge](https://mlsanity.com/paper/2107.10922/) (2021)
- [NeuroComparatives: Neuro-Symbolic Distillation of Comparative Knowledge](https://mlsanity.com/paper/2305.04978/) (2023)
- [What's the best place for an AI conference, Vancouver or ______: Why completing comparative questions is difficult](https://mlsanity.com/paper/2104.01940/) (2021)
- [ImageNetVC: Zero- and Few-Shot Visual Commonsense Evaluation on 1000 ImageNet Categories](https://mlsanity.com/paper/2305.15028/) (2023)
- [Benchmarking Large and Small MLLMs](https://mlsanity.com/paper/2501.04150/) (2025)
- [Inferring spatial relations from textual descriptions of images](https://mlsanity.com/paper/2102.00997/) (2021)
- [Grounding Spatial Relations in Text-Only Language Models](https://mlsanity.com/paper/2403.13666/) (2024)
- [LaMI: Augmenting Large Language Models via Late Multi-Image Fusion](https://mlsanity.com/paper/2406.13621/) (2024)
- [Semantic Novelty Detection and Characterization in Factual Text Involving Named Entities](https://mlsanity.com/paper/2210.17440/) (2022)
- [Plausible-Parrots @ MSP2023: Enhancing Semantic Plausibility Modeling using Entity and Event Knowledge](https://mlsanity.com/paper/2408.16937/) (2024)
- [Improving the Efficiency of Visually Augmented Language Models](https://mlsanity.com/paper/2409.11148/) (2024)
- [Plausibility Vaccine: Injecting LLM Knowledge for Event Plausibility](https://mlsanity.com/paper/2503.12667/) (2025)
- [TComQA: Extracting Temporal Commonsense from Text](https://mlsanity.com/paper/2508.15274/) (2025)
- [CALIPER: Metric-Grounded Model-Free Recognition of Visually Similar Industrial Parts](https://mlsanity.com/paper/2609.17820/) (2026)

## Abstract (arXiv)

Human vision greatly benefits from the information about sizes of objects. The role of size in several visual reasoning tasks has been thoroughly explored in human perception and cognition. However, the impact of the information about sizes of objects is yet to be determined in AI. We postulate that this is mainly attributed to the lack of a comprehensive repository of size information. In this paper, we introduce a method to automatically infer object sizes, leveraging visual and textual information from web. By maximizing the joint likelihood of textual and visual observations, our method learns reliable relative size estimates, with no explicit human supervision. We introduce the relative size dataset and show that our method outperforms competitive textual and visual baselines in reasoning about size comparisons.