Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Neural Naturalist: Generating Fine-Grained Image Comparisons

About

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.

Maxwell Forbes, Christine Kaeser-Chen, Piyush Sharma, Serge Belongie• 2019

Related benchmarks

TaskDatasetResultRank
Pairwise taxonomic verification accuracyBirds-to-Words
Visual Accuracy55
7
Showing 1 of 1 rows

Other info

Follow for update