Neural Naturalist: Generating Fine-Grained Image Comparisons
This work addresses the need for detailed image comparisons to aid citizen scientists in biodiversity preservation, though it is incremental in applying existing neural methods to a new dataset.
The paper tackled the problem of generating fine-grained comparative descriptions of bird images by introducing the Birds-to-Words dataset and the Neural Naturalist model, with results showing promising potential for neural models to explain visual differences using natural language.
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.