mlsanityData to 7 Oct 2026

Neural Naturalist: Generating Fine-Grained Image Comparisons

arXiv 1909.04101 ↗First posted 9 Sep 2019cs.CL cs.CVcited by 36

Not on the map. Why?

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.

Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 4; 2023: 3; 2024: 11; 2025: 10; 2026: 3.

36 papers.

Sort:

By area:

  1. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,669
  2. 2021Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Modelscited by 244
  3. 2024MANTIS: Interleaved Multi-Image Instruction Tuningcited by 212
  4. 2023Zero-Shot Composed Image Retrieval with Textual Inversioncited by 171
  5. 2021Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Colorcited by 118
  6. 2023Fine-tuning Multimodal LLMs to Follow Zero-shot Demonstrative Instructionscited by 76
  7. 2024MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuningcited by 75
  8. 2024Spherical Linear Interpolation and Text-Anchoring for Zero-shot Composed Image Retrievalcited by 44
  9. 2023Expert Knowledge-Aware Image Difference Graph Representation Learning for Difference-Aware Medical Visual Question Answeringcited by 41
  10. 2022Image Difference Captioning with Pre-training and Contrastive Learningcited by 39
  11. 2024MC-Bench: A Benchmark for Multi-Context Visual Grounding in the Era of MLLMscited by 38
  12. 2021RTIC: Residual Learning for Text and Image Composition using Graph Convolutional Networkcited by 27
24 more
  1. 2022Image Retrieval from Contextual Descriptionscited by 26
  2. 2022CLIP4IDC: CLIP for Image Difference Captioningcited by 25
  3. 2024iSEARLE: Improving Textual Inversion for Zero-Shot Composed Image Retrievalcited by 24
  4. 2024EgoCVR: An Egocentric Benchmark for Fine-Grained Composed Video Retrievalcited by 21
  5. 2025A Comprehensive Survey on Composed Image Retrievalcited by 17
  6. 2024OneDiff: A Generalist Model for Image Difference Captioningcited by 15
  7. 2021FixMyPose: Pose Correctional Captioning and Retrievalcited by 12
  8. 2025OmniDiff: A Comprehensive Benchmark for Fine-grained Image Difference Captioningcited by 12
  9. 2024Step Differences in Instructional Videocited by 11
  10. 2021L2C: Describing Visual Differences Needs Semantic Understanding of Individualscited by 8
  11. 2025ConText-CIR: Learning from Concepts in Text for Composed Image Retrievalcited by 7
  12. 2022Training and challenging models for text-guided fashion image retrievalcited by 5
  13. 2024A Survey of Multimodal Composite Editing and Retrievalcited by 5
  14. 2025Same or Not? Enhancing Visual Perception in Vision-Language Modelscited by 5
  15. 2024Pseudo-triplet Guided Few-shot Composed Image Retrievalcited by 4
  16. 2025good4cir: Generating Detailed Synthetic Captions for Composed Image Retrievalcited by 4
  17. 2025Breaking Language Barriers in Visual Language Models via Multilingual Textual Regularizationcited by 4
  18. 2026VLM-SubtleBench: How Far Are VLMs from Human-Level Subtle Comparative Reasoning?cited by 4
  19. 2025Top-Down Compression: Revisit Efficient Vision Token Projection for Visual Instruction Tuningcited by 3
  20. 2025Composed Multi-modal Retrieval: A Survey of Approaches and Applicationscited by 2
  21. 2026SPD-Faith Bench: Diagnosing and Improving Faithfulness in Chain-of-Thought for Multimodal Large Language Modelscited by 2
  22. 2025Image Difference Grounding with Natural Languagecited by 1
  23. 2025Analyze-Prompt-Reason: A Collaborative Agent-Based Framework for Multi-Image Vision-Language Reasoningcited by 1
  24. 2026DiffSpot: Can VLMs Spot Fine-Grained Visual Differences in Web Interfaces?cited by 1