Improved Bird Species Recognition Using Pose Normalized Deep Convolutional Nets

By Steve Branson, Grant Van Horn, Pietro Perona, Serge J. Belongie. 2014

124 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Ecological Modeling, Ecology, Genetics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Dacheng Tao
3. Ming-Hsuan Yang
4. Xiaogang Wang
5. Trevor Darrell
6. Yi Yang
7. Bernt Schiele
8. Andrew Zisserman

In Ecological Modeling

1. Pietro Perona
2. Grant Van Horn

In Ecology

1. Shuicheng Yan
2. Xiao Wu
3. Jianfei Cai
4. Pietro Perona
5. Bo Zhao
6. Jonathan Krause
7. Grant Van Horn
8. Jiashi Feng

In Genetics

1. Ahmed M. Elgammal
2. Pietro Perona

Citations in the corpus

• Recent advances in convolutional neural networks (2015, methodology): “[104] propose a method which detects parts and extracts CNN features from multiple pose-normalized regions.”
• The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition (2015, background): “Fine-grained recognition refers to the task of distinguishing very similar categories, such as breeds of dogs [23, 31], species of birds [54, 52, 5, 3], or models of cars [61, 25].”
• Deep Image: Scaling up Image Recognition (2015, background): “are pre-trained on ILSVRC and then fine-tuned of all the layers with CUB-200-2011 dataset at the resolution of 256x256 and 512x512 respectively. The result is better than all previous work except one [4], despite the fact that no part or bounding box annotations were used. We achieved accuracy of 85”
• The Devil is in the Tails: Fine-grained Classification in the Wild (2017, background): “Most fine-grained research papers present a novel model for classification [4, 6, 7, 12, 15, 17, 25, 31, 40, 45, 46, 57, 58, 59, 61, 62].”
• SPDA-CNN: Unifying Semantic Part Detection and Abstraction for Fine-Grained Recognition (2016, methodology): “In order to introduce such layers to facilitate the extraction of part-specific features, several works proposed part-based CNN methods [41, 5, 28, 39].”
• Diversified Visual Attention Networks for Fine-Grained Object Classification (2016, background): “a prototype image, lower-level features with normalized poses and higher-level features with unaligned images are integrated for bird species categorization in [39].”