Birdsnap: Large-Scale Fine-Grained Visual Categorization of Birds

By Thomas Berg, Jiongxin Liu, Seung Woo Lee, Michelle L. Alexander, David W. Jacobs, Peter N. Belhumeur. 2014

411 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Developmental Biology, Ecological Modeling, Ecology

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. Trevor Darrell
4. Xiaogang Wang
5. Ming-Hsuan Yang
6. Yi Yang
7. Andrew Zisserman
8. Jitendra Malik

In Developmental Biology

1. Yuxin Peng
2. Feng Zhou
3. Yuanqing Lin
4. Xiangteng He
5. Serge J. Belongie
6. Ryan Farrell
7. Heliang Zheng
8. Jianlong Fu

In Ecological Modeling

1. Serge J. Belongie
2. Ben. G. Weinstein
3. Pietro Perona
4. Grant Van Horn
5. Jian Pu
6. Xiangyang Xue
7. Yu-Gang Jiang
8. Oisin Mac Aodha

In Ecology

1. Yuxin Peng
2. Xiangteng He
3. Feng Zhou
4. Yuanqing Lin
5. Ben. G. Weinstein
6. Jianlong Fu
7. Heliang Zheng
8. Xiao Liu

Citations in the corpus

• Do Better ImageNet Models Transfer Better? (2018, background): “These datasets covered a wide range of image classification tasks, including superordinate-level object classification (CIFAR-10 [37], CIFAR-100 [37], PASCAL VOC 2007 [19], Caltech-101 [20]); fine-grained object classification (Food-101 [5], Birdsnap [4], Stanford Cars [36], FGVC Aircraft [48], Oxfo”
• Fixing the train-test resolution discrepancy (2019, methodology): “We evaluated it on the following datasets: iNaturalist 2017 [16], Stanford Cars [19], CUB-200-2011 [40], Oxford 102 Flowers [26], Oxford-IIIT Pets [28], NABirds [39] and Birdsnap [4].”
• Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning (2020, methodology): “[90] Thomas Berg, Jiongxin Liu, Seung Woo Lee, Michelle L.”
• Fine-Grained Image Classification via Combining Vision and Language (2017, background): “And on the data side, more fine-grained domains have been covered, such as bird types [6, 7], dog species [8], plant breeds [9] , car types [10] and aircraft models [11].”
• CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP (2021, background): “This set contains Birdsnap (Berg et al., 2014), Country211 (Radford et al.”
• Florence: A New Foundation Model for Computer Vision (2021, background): “Note that our benchmarks exclude the Birdsnap (Berg et al., 2014) dataset from 12 original classification datasets introduced in (Kornblith et al., 2019), because 20% of the image URLs provided by the authors are invalid.”
• Recent advances in convolutional neural networks (2015, background): “There are already some finegrained image datasets (such as Flower [98], Birds [99], [100], Dogs [101], Cars [102] and Shoes [103]).”
• AutoHAS: Differentiable Hyper-parameter and Architecture Search (2020, methodology): “We demonstrate the effectiveness of our AutoHAS on five vision datasets, i.e., ImageNet [7], Birdsnap [3], CIFAR-10, CIFAR-100 [29], and Cars [28], and a NLP dataset, i.e., SQuAD 1.1 [39].”
• The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition (2015, methodology): “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].”
• How Well Does Self-Supervised Pre-Training Perform with Streaming Data? (2021, positive): “Following (Chen et al., 2020a), we consider 12 diverse image classification datasets including Food-101 (Bossard et al., 2014), CIFAR10 (Krizhevsky et al., 2009), CIFAR100 (Krizhevsky et al., 2009), Birdsnap (Berg et al., 2014), SUN397 (Xiao et al., 2010), Standard Cars (Krause et al., 2013), FGVC Ai”
• Class-incremental Learning via Deep Model Consolidation (2019, methodology): “We use BirdSnap [3] as the auxiliary data source where we excluded the CUB categories.”
• Domain Adaptive Transfer Learning with Specialist Models (2018, neutral): “CIFAR-10 [18] 50,000 10,000 10 Birdsnap [4] 47,386 2,443 78 Stanford Cars [16] 8,144 8,041 196 FGVC Aircraft [21] 6,667 3,333 100 Oxford-IIIT Pets [23] 3,680 3,369 37 Food-101 [5] 75,750 25,250 101”
• The Devil is in the Tails: Fine-grained Classification in the Wild (2017, background): “The vision community has released many fine-grained datasets covering several domains such as birds [5, 50, 52, 56], dogs [23, 34], airplanes [36, 51], flowers [37], leaves [28], trees [55] and cars[24, 32].”
• Bird Species Categorization Using Pose Normalized Deep Convolutional Nets (2014, background): “Areas explored include feature representations that better preserve fine-grained information [35, 46, 47, 48], segmentation-based approaches [1, 13, 14, 15, 21, 37] that facilitate extraction of purer features, and part/pose normalized feature spaces [5, 6, 19, 33, 38, 39, 43, 50, 51].”
• The iNaturalist Challenge 2017 Dataset (2017, background): “The vision community has released many fine-grained datasets covering several domains such as birds [42, 40, 2, 38, 16], dogs [14, 28, 22], airplanes [23, 39], flowers [26], leaves [18], trees [41] and cars [17, 20, 46, 6].”
• A Benchmark for Interpretability Methods in Deep Neural Networks (2018, methodology): “We applied ROAR in a broad set of experiments across three large scale, open source image datasets: ImageNet [11], Food 101 [9] and Birdsnap [8].”
• Scalable Transfer Learning with Expert Models (2020, background): “The second suite is a collection of popular natural datasets commonly used in transfer learning literature: FGVC-Aircraft [38], Birdsnap [5], CIFAR10 [31], Stanford Cars [30], Food [7], and Oxford IIIT Pets [47].”