One-shot learning of object categories

By Li Fei-Fei, Rob Fergus, Pietro Perona. 2006

3,355 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Representation & Self-Supervised Learning

Citations in the corpus

On Robustness and Transferability of Convolutional Neural Networks (2020, background): “The Natural group contains the following datasets: Caltech101 [40], CIFAR-100 [36], DTD [9], Flowers102 [45], Pets [47], Sun397 [65], SVHN [44].”
A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark (2019, background): “Improving sample efﬁciency has been approached from many angles: few-shot learning (Fei-Fei et al., 2006), transfer learning (Pan & Yang, 2009), domain adaptation (Wang & Deng, 2018), and representation learning (Bengio et al., 2013).”
Learning Visual N-Grams from Web Data (2016, background): “This tradition dates back to early image-recognition benchmarks such as CalTech-101 [18] but is still common in modern benchmarks such as ImageNet [47] and COCO [42].”
Visualizing and Understanding Convolutional Networks (2013, methodology): “We now explore the ability of these feature extraction layers to generalize to other datasets, namely Caltech-101 (Fei-fei et al., 2006), Caltech-256 (Griﬃn et al., 2006) Table 3.”
Zero-Shot Learning Through Cross-Modal Transfer (2013, methodology): “Their model uses both local context in the window around each word and global document context.”
DeepSetNet: Predicting Sets with Deep Neural Networks (2016, background): “Early datasets, such as Caltech-101 [7], mostly contained one single object and could easily be described by one category.”
Benchmarking Deep Reinforcement Learning for Continuous Control (2016, neutral): “, 1998), Caltech101 (Fei-Fei et al., 2006), CIFAR (Krizhevsky & Hinton, 2009), ImageNet (Deng et al.”
LVIS: A Dataset for Large Vocabulary Instance Segmentation (2019, methodology): “We owe much of our current success in image recognition to pioneering datasets such as MNIST [16], BSDS [20], Caltech 101 [6], PASCAL VOC [5], ImageNet [23], and Toy Deer”
Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks (2015, neutral): “class ifor which the count of examples that were classiﬁed as y k and belonged to c i was maximal. This setup hence bears some similarity to one-shot learning approaches from the literature (see e.g. Fei-Fei et al. (2006) for an application to computer vision). Since no learning is involved in the a”
CrossTransformers: spatially-aware few-shot transfer (2020, background): “Few-shot learning [25, 35, 46, 53] has recently been primarily addressed in the meta-learning framework [57, 71, 80], where a model learns an update rule for the parameters of a base-learner model [6, 7, 72] through a sequence of training episodes [79, 88].”
Meta-Learning Probabilistic Inference for Prediction (2018, background): “These applications have given rise to vast interest in few-shot learning (Fei-Fei et al., 2006; Lake et al., 2011), which emphasizes data efficiency via information sharing across related tasks.”
Meta-learning with differentiable closed-form solvers (2018, methodology): “K samples (shots) per class, while the test-set by Q query/test images per class (using numenclature from [6, 4]).”
Visual Prompt Tuning (2022, neutral): “800/1000 200 10,000 Caltech101 [43] 102 6,084 DTD [11] 47 1,880 Flowers102 [55] 102 6,149 Pets [57] 37 3,669 SVHN [54] 10 26,032 Sun397 [76] 397 21,750 Patch Camelyon [69] Specialized 2 800/1000 200 32,768 EuroSAT [29] 10 5,400 Resisc45 [10] 45 6,300 Retinopathy [36] 5 42,670 Clevr/count [34]”
The Open Images Dataset V4 (2018, background): “Open Images V4 has several attractive characteristics, compared to previously available datasets in these areas (Krizhevsky, 2009; Fei-Fei et al., 2006; Griffin et al., 2007; Deng et al., 2009; Russakovsky et al., 2015; Everingham et al., 2012; Gupta and Malik, 2015; Krishna et al., 2017).”
YouTube-8M: A Large-Scale Video Classification Benchmark (2016, methodology): “Starting from a number of well labeled small-scale datasets such as Caltech 101/256 [8, 10], MSRC [32], PASCAL [7], image understanding research has rapidly advanced to utilizing larger datasets such as ImageNet [6] and SUN [38] for the next generation of vision algorithms.”