Fine-grained Recognition Datasets for Biodiversity Analysis

Abstract

In the following paper, we present and discuss challenging applications for fine-grained visual classification (FGVC): biodiversity and species analysis. We not only give details about two challenging new datasets suitable for computer vision research with up to 675 highly similar classes, but also present first results with localized features using convolutional neural networks (CNN). We conclude with a list of challenging new research directions in the area of visual classification for biodiversity research.

CVPR FGVC Workshop 2015; dataset available

References in corpus (1)

• Bird Species Categorization Using Pose Normalized Deep Convolutional Nets

Cited by in corpus (7)

• Weakly Supervised Fine-Grained Image Categorization
• Automatic identification of fossils and abiotic grains during carbonate microfacies analysis using deep convolutional neural networks
• Selective Convolutional Descriptor Aggregation for Fine-Grained Image Retrieval
• CoCoNet: A Collaborative Convolutional Network
• PProCRC: Probabilistic Collaboration of Image Patches
• Past, Present, and Future Approaches Using Computer Vision for Animal Re-Identification from Camera Trap Data
• Distance Metric Learned Collaborative Representation Classifier