# Neural Naturalist: Generating Fine-Grained Image Comparisons

arXiv: https://arxiv.org/abs/1909.04101 · HTML: https://mlsanity.com/paper/1909.04101/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Sep 2019.

## Built on by (most cited first, 30 of 36)

- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models](https://mlsanity.com/paper/2108.04024/) (2021)
- [MANTIS: Interleaved Multi-Image Instruction Tuning](https://mlsanity.com/paper/2405.01483/) (2024)
- [Zero-Shot Composed Image Retrieval with Textual Inversion](https://mlsanity.com/paper/2303.15247/) (2023)
- [Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color](https://mlsanity.com/paper/2109.06129/) (2021)
- [Fine-tuning Multimodal LLMs to Follow Zero-shot Demonstrative Instructions](https://mlsanity.com/paper/2308.04152/) (2023)
- [MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning](https://mlsanity.com/paper/2409.20566/) (2024)
- [Spherical Linear Interpolation and Text-Anchoring for Zero-shot Composed Image Retrieval](https://mlsanity.com/paper/2405.00571/) (2024)
- [Expert Knowledge-Aware Image Difference Graph Representation Learning for Difference-Aware Medical Visual Question Answering](https://mlsanity.com/paper/2307.11986/) (2023)
- [Image Difference Captioning with Pre-training and Contrastive Learning](https://mlsanity.com/paper/2202.04298/) (2022)
- [MC-Bench: A Benchmark for Multi-Context Visual Grounding in the Era of MLLMs](https://mlsanity.com/paper/2410.12332/) (2024)
- [RTIC: Residual Learning for Text and Image Composition using Graph Convolutional Network](https://mlsanity.com/paper/2104.03015/) (2021)
- [Image Retrieval from Contextual Descriptions](https://mlsanity.com/paper/2203.15867/) (2022)
- [CLIP4IDC: CLIP for Image Difference Captioning](https://mlsanity.com/paper/2206.00629/) (2022)
- [iSEARLE: Improving Textual Inversion for Zero-Shot Composed Image Retrieval](https://mlsanity.com/paper/2405.02951/) (2024)
- [EgoCVR: An Egocentric Benchmark for Fine-Grained Composed Video Retrieval](https://mlsanity.com/paper/2407.16658/) (2024)
- [A Comprehensive Survey on Composed Image Retrieval](https://mlsanity.com/paper/2502.18495/) (2025)
- [OneDiff: A Generalist Model for Image Difference Captioning](https://mlsanity.com/paper/2407.05645/) (2024)
- [FixMyPose: Pose Correctional Captioning and Retrieval](https://mlsanity.com/paper/2104.01703/) (2021)
- [OmniDiff: A Comprehensive Benchmark for Fine-grained Image Difference Captioning](https://mlsanity.com/paper/2503.11093/) (2025)
- [Step Differences in Instructional Video](https://mlsanity.com/paper/2404.16222/) (2024)
- [L2C: Describing Visual Differences Needs Semantic Understanding of Individuals](https://mlsanity.com/paper/2102.01860/) (2021)
- [ConText-CIR: Learning from Concepts in Text for Composed Image Retrieval](https://mlsanity.com/paper/2505.20764/) (2025)
- [Training and challenging models for text-guided fashion image retrieval](https://mlsanity.com/paper/2204.11004/) (2022)
- [A Survey of Multimodal Composite Editing and Retrieval](https://mlsanity.com/paper/2409.05405/) (2024)
- [Same or Not? Enhancing Visual Perception in Vision-Language Models](https://mlsanity.com/paper/2512.23592/) (2025)
- [Pseudo-triplet Guided Few-shot Composed Image Retrieval](https://mlsanity.com/paper/2407.06001/) (2024)
- [good4cir: Generating Detailed Synthetic Captions for Composed Image Retrieval](https://mlsanity.com/paper/2503.17871/) (2025)
- [Breaking Language Barriers in Visual Language Models via Multilingual Textual Regularization](https://mlsanity.com/paper/2503.22577/) (2025)
- [VLM-SubtleBench: How Far Are VLMs from Human-Level Subtle Comparative Reasoning?](https://mlsanity.com/paper/2603.07888/) (2026)

## Abstract (arXiv)

We introduce the new Birds-to-Words dataset of 41k sentences describing fine-grained differences between photographs of birds. The language collected is highly detailed, while remaining understandable to the everyday observer (e.g., "heart-shaped face," "squat body"). Paragraph-length descriptions naturally adapt to varying levels of taxonomic and visual distance---drawn from a novel stratified sampling approach---with the appropriate level of detail. We propose a new model called Neural Naturalist that uses a joint image encoding and comparative module to generate comparative language, and evaluate the results with humans who must use the descriptions to distinguish real images. Our results indicate promising potential for neural models to explain differences in visual embedding space using natural language, as well as a concrete path for machine learning to aid citizen scientists in their effort to preserve biodiversity.