Novel Dataset for Fine-Grained Image Categorization : Stanford Dogs

By Aditya Khosla, Nityananda Jayadevaprakash, Bangpeng Yao, Li Fei-Fei. 2012

1,666 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Evaluation & Benchmarks

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

In Evaluation & Benchmarks

Citations in the corpus

ImageNet Large Scale Visual Recognition Challenge (2014, methodology): “A subset of categories and images was chosen and 3 In addition, ILSVRC in 2012 also included a taster finegrained classification task, where algorithms would classify dog photographs into one of 120 dog breeds (Khosla et al., 2011).”
Projected GANs Converge Faster (2021, methodology): “We compare on LSUN cat and horse [84], ADE indoor (a subset of ADE [91] proposed in [3]), the full Oxford ﬂowers dataset with 8k images [56], KITTI-ﬁsheye (a subset of KITTI-360 [46], consisting of ﬁsheye images), STL-10 [8], CUB200 [80], Stanford Dogs [36], and Stanford Cars [42].”
Fine-Grained Visual Classification of Aircraft (2013, background): “Airplanes are an alternative to objects typically considered in ﬁne-grained visual classiﬁcation (FGVC) such as birds [5] and pets [2–4].”
Visual Prompt Tuning (2022, methodology): “Dataset Description # Classes Train Val Test Fine-grained visual recognition tasks (FGVC) CUB-200-2011 [70] Fine-grained bird species recognition 200 5,394 600 5,794 NABirds [67] Fine-grained bird species recognition 55 21,536 2,393 24,633 Oxford Flowers [55] Fine-grained flower species recognition ”
NDD20: A large-scale few-shot dolphin dataset for coarse and fine-grained categorisation (2020, background): “Datasets often focus on a particular subset of animals such as pets commonly found in homes (9, 12) or birds (14, 17).”
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications (2017, methodology): “We train MobileNet for fine grained recognition on the Stanford Dogs dataset [17].”
Part-Based R-CNNs for Fine-Grained Category Detection (2014, background): “Recently, a large body of computer vision research has focused on the finegrained classification problem in a number of domains, such as animal breeds or species [16, 26, 31, 33, 37, 46], plant species [1, 2, 5, 34, 35, 39], and man-made objects [32, 40].”
Certifying Some Distributional Robustness with Principled Adversarial Training (2017, methodology): “For the more realistic Stanford Dogs dataset [35], we ﬁrst present results where we ran Algorithm 1 on a semantic feature space with γ chosen large enough to satisfy bounds given in Section 4.”
Recent advances in convolutional neural networks (2015, background): “There are already some ﬁne-grained image datasets (such as Flower [99], Birds [100], [101], Dogs [102], Cars [103] and Shoes [104]).”
The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition (2015, methodology): “Second, we show that by simply using noisy, publiclyavailable data from the web, we can greatly exceed existing state-of-the-art methods on four fine-grained datasets [54, 3, 33, 23] without any domain-specific modeling, and even without using associated heavily-curated training sets.”
Neural Activation Constellations: Unsupervised Part Model Discovery with Convolutional Networks (2015, positive): “For fine-grained classification, we evaluate our approach on CUB200-2011 [33] (200 classes, 11788 images), Stanford dogs [20] (120 classes, 20580 images), Oxford flowers 102 [24] (102 classes, 8189 images), and OxfordIIIT Pets [25] (37 classes, 7349 images).”
The Devil is in the Tails: Fine-grained Classification in the Wild (2017, background): “Fine-Grained Visual Classification – 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].”
Learning Adaptive Classifiers Synthesis for Generalized Few-Shot Learning (2019, methodology): “We construct a Heterogeneous dataset based on 5 fine-grained classification datasets, namely AirCraft [32], Car-196 [19], Caltech-UCSD Birds (CUB) 200-2011 [48], Stanford Dog [18], and Indoor Scenes [35].”
Attention for Fine-Grained Categorization (2014, methodology): “We apply the visual attention model from Ba et al. (2014) to the Stanford Dogs ﬁne-grained categorization task (Khosla et al., 2011), choosing to perform the task without using the provided bounding boxes for training or testing.”
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].”
Explaining the Unexplained: A CLass-Enhanced Attentive Response (CLEAR) Approach to Understanding Deep Neural Networks (2017, methodology): “We conducted qualitative and quantitative experiments on three different datasets: the commonly used benchmarks MNIST and Street View House Numbers (SVHN), and the Stanford Dog dataset [8].”
Explicit Inductive Bias for Transfer Learning with Convolutional Networks (2018, background): “2007) contains different objects for generic object recognition; MIT Indoors 67 (Quattoni & Torralba 2009) consists of 67 indoor scene categories; Stanford Dogs 120 (Khosla et al. 2011) contains images of 120 breeds of dogs; Each target database is split into training and testing sets following the ”
The importance of better models in stochastic optimization (2019, methodology): “Therefore, in our last set of experiments, we test the performance of our models for training neural networks for classification tasks over the CIFAR10 dataset (34) and the fine-grained 128-class Stanford dog multiclass recognition task (35).”