Matching Networks for One Shot Learning
By Oriol Vinyals, Charles Blundell, Timothy P. Lillicrap, Koray Kavukcuoglu, Daan Wierstra. 2016
8,487 citations recorded by the source corpus.
Learning from a few examples remains a key challenge in machine learning. Despite recent advances in important domains such as vision and language, the standard supervised deep learning paradigm does not offer a satisfactory solution for learning new concepts rapidly from little data. In this work, we employ ideas from metric learning based on deep neural features and from recent advances that augment neural networks with external memories. Our framework learns a network that maps a small labelled support set and an unlabelled example to its label, obviating the need for fine-tuning to adapt to new class types. We then define one-shot learning problems on vision (using Omniglot, ImageNet) and language tasks. Our algorithm improves one-shot accuracy on ImageNet from 87.6% to 93.2% and from 88.0% to 93.8% on Omniglot compared to competing approaches. We also demonstrate the usefulness of the same model on language modeling by introducing a one-shot task on the Penn Treebank.
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
- Sergey Levine
- Yoshua Bengio
- Mohit Bansal
- Jianfeng Gao
- Quoc V. Le
- Percy Liang
- Trevor Darrell
- Ruslan Salakhutdinov
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Dacheng Tao
- Trevor Darrell
- Ming-Hsuan Yang
- Xiaogang Wang
- Bernt Schiele
- Jitendra Malik
- Andrew Zisserman
In Representation & Self-Supervised Learning
- Yoshua Bengio
- Trevor Darrell
- Han-Jia Ye
- Dacheng Tao
- De-chuan Zhan
- Andrea Vedaldi
- Sergey Levine
- Bernt Schiele
Citations in the corpus
- Language Models are Few-Shot Learners (2020, methodology): “As indicated by the name, few-shot learning as described here for language models is related to few-shot learning as used in other contexts in ML [HYC01, VBL + 16] – both involve learning based on a broad distribution of tasks and then rapidly adapting to a new task.”
- Few-shot Learning with Retrieval Augmented Language Models (2022, background): “Few-shot learning, the task of learning from very few examples, has been studied for decades (Thrun & Pratt, 1998; Fink, 2005; Vinyals et al., 2016), but has recently seen an explosion of interest in NLP with the arrival of large pre-trained models, which exhibit emergent few-shot learning…”
- Meta-Learning for Low-Resource Neural Machine Translation (2018, background): “…of meta-learning: 1. learning a meta-policy for updating model parameters (see, e.g., Andrychowicz et al., 2016; Ha et al., 2016a; Mishra et al., 2017) 2. learning a good parameter initialization for fast adaptation (see, e.g., Finn et al., 2017; Vinyals et al., 2016; Snell et al., 2017).”
- Few-shot Autoregressive Density Estimation: Towards Learning to Learn Distributions (2017, methodology): “This setting, called few-shot learning, has been studied using deep neural networks and many other approaches in the context of discriminative models, for example Vinyals et al. (2016); Santoro et al. (2016).”
- RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning (2016, background): “Our work draws inspiration from a particular line of work (Younger et al., 2001; Santoro et al., 2016; Vinyals et al., 2016), which formulates meta-learning as an optimization problem, and can thus be optimized end-to-end via gradient descent.”
- Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges (2019, background): “Other problems closely related to multitask learning include zero or few-shot learning (Lake et al., 2011; Romera-Paredes and Torr, 2015; Vinyals et al., 2016; Pan and Yang, 2010), meta-learning and life-long learning (Thrun and Mitchell, 1995; Silver et al., 2013; Chen and Liu, 2016; Parisi et…”
- Do Better ImageNet Models Transfer Better? (2018, methodology): “This problem is closely related to few-shot learning [39, 71, 55, 62, 21, 62, 49], but these methods are typically evaluated with training and test classes from the same distribution.”
- Growing a Brain: Fine-Tuning by Increasing Model Capacity (2017, background): “Transfer learning is related to both multi-task learning [32, 4, 28, 10, 11, 45, 24, 2] and learning novel categories from few examples [49, 19, 21, 35, 51, 22, 5, 13, 50, 47, 31].”
- Making Pre-trained Language Models Better Few-shot Learners (2021, methodology): “This is reminiscent of Matching Networks (Vinyals et al., 2016), and more specifically BERT-PAIR (Gao et al.”
- Big Transfer (BiT): General Visual Representation Learning (2019, background): “Metalearning or metric-learning techniques have been proposed to learn with few or no labels [59,49,52].”
- Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need? (2020, methodology): “Matching Networks [55] employed two networks for query samples and support samples respectively and used an LSTM with read-attention to encode a full context embedding of support samples.”
- Learning with Latent Language (2017, neutral): “Closely related meta-learning approaches (e.g. Schmidhuber, 1987; Santoro et al., 2016; Vinyals et al., 2016) make use of the same data, but collapse the inner optimization over θ(c) and prediction of y(e) into a single learned model.”
- What can the brain teach us about building artificial intelligence? (2016, background): “& Wierstra, D. (2014) Stochastic backpropagation and approximate inference in deep generative models.”
- One-Shot Imitation Learning (2017, background): “One-shot and few-shot learning has been studied for image recognition (Vinyals et al., 2016; Koch, 2015; Santoro et al., 2016; Ravi & Larochelle, 2017), generative modeling (Edwards & Storkey, 2017; Rezende et al., 2016), learning “fast” reinforcement learning agents with recurrent policies (Duan…”
- Repurposing Pretrained Models for Robust Out-of-domain Few-Shot Learning (2021, methodology): “We train MAML on mini ImageNet (Vinyals et al., 2016) training split; we then apply our method on the resulting checkpoint.”
- Comparison of Maximum Likelihood and GAN-based training of Real NVPs (2017, methodology): “We will take ideas from supervised setting where people used a short-term memory to provide one-shot learning (Santoro et al., 2016; Vinyals et al., 2016).”