The Caltech-UCSD Birds-200-2011 Dataset

By Catherine Wah, Steve Branson, Peter Welinder, Pietro Perona, Serge J. Belongie. 2011

5,149 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

Growing a Brain: Fine-Tuning by Increasing Model Capacity (2017, methodology): “…available baselines and report multi-class Tasks and datasets: We evaluate on standard benchmark datasets for scene classiﬁcation: MIT-67 [44], for ﬁne-grained recognition: Caltech-UCSD Birds (CUB) 200 - 2011 [48] and Oxford 102 Flowers [27], and for action recognition: Stanford-40 actions [54].”
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].”
ALICE: Active Learning with Contrastive Natural Language Explanations (2020, methodology): “Dataset We use the CUB-200-2011 dataset (Wah et al., 2011), which contains 11, 788 images for 200 species of North American birds.”
Learning Visual Representations with Caption Annotations (2020, background): “tasks. However, this approach has major limitations. First, the cost and complexity of annotating datasets is considerable, especially when the class taxonomy is ne-grained requiring expert knowledge [12,44,60]. Second, retraining from scratch dedicated models for every new task is inecient. Some al”
Shaping Visual Representations with Language for Few-Shot Classification (2019, positive): “To see if LSL can scale to more realistic scenarios, we use the Caltech-UCSD Birds dataset (Wah et al., 2011), which contains 200 bird species, each with 40–60 images, split into 100 train, 50 validation, and 50 test classes.”
Fine-Grained Image Classification via Combining Vision and Language (2017, methodology): “2011. Note that it is a technically challenging task even for humans to categorize them due to large intra-class variance and small inter-class variance. domains have been covered, such as bird types [6,7], dog species [8], plant breeds [9] , car types [10] and aircraft models [11].It is easy for an”
Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations (2016, background): “Attributes have also played a large role in improving fine-grained recognition (Goering et al., 2014) on fine-grained attribute datasets like CUB-2011 (Wah et al., 2011).”
Spatial Transformer Networks (2015, methodology): “3, we investigate the use of multiple parallel spatial transformers for fine-grained classification, showing state-of-the-art performance on CUB-200-2011 birds dataset [28] by automatically discovering object parts and learning to attend to them.”
Grafit: Learning fine-grained image representations with coarse labels (2020, background): “Fine-grained classification datasets [29] have been developed for specific domains, for instance to distinguish different plants [13] or bird species [59].”
CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features (2019, methodology): “On the localization front, CutMix improves the performance of the weakly-supervised object localization (WSOL) task on CUB200-2011 [43] and ImageNet [30] by +5.”
Towards Language-Free Training for Text-to-Image Generation (2021, methodology): “We consider a suite of datasets that are commonly used in literature [53, 54, 56, 59], including MSCOCO [4], CUB [47], LN-COCO [36], Multi-modal CelebA-HQ (MM CelebA-HQ) [52].”
Generative Adversarial Text to Image Synthesis (2016, methodology): “Recently, deep convolutional and recurrent networks for text have yielded highly discriminative and generalizable (in the zero-shot learning sense) text representations learned automatically from words and characters (Reed et al., 2016).”
Cross-Modal Contrastive Learning for Text-to-Image Generation (2021, background): “, birds [56] and flowers [35]), but struggle on complex scenes with many objects—such as those in MS-COCO [30].”
DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-To-Image Synthesis (2019, methodology): “ted the DM-GAN model using the open-source Python library PyTorch [18]. Datasets. To demonstrate the capability of our proposed method for text-to-image synthesis, we conducted experiments on the CUB [26] and the COCO [11] datasets. The CUB dataset contains 200 bird categories with 11,788 images, wh”
AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks (2017, methodology): “Same as previous text-to-image methods [36, 37, 20, 18], our method is evaluated on CUB [29] and COCO [14] datasets.”
Unsupervised Embedding Learning via Invariant and Spreading Instance Feature (2019, methodology): “200 (CUB200) [43] is a fine-grained bird dataset.”