Learning feed-forward one-shot learners

By Luca Bertinetto, João F. Henriques, Jack Valmadre, Philip H. S. Torr, Andrea Vedaldi. 2016

494 citations recorded by the source corpus.

One-shot learning is usually tackled by using generative models or discriminative embeddings. Discriminative methods based on deep learning, which are very effective in other learning scenarios, are ill-suited for one-shot learning as they need large amounts of training data. In this paper, we propose a method to learn the parameters of a deep model in one shot. We construct the learner as a second deep network, called a learnet, which predicts the parameters of a pupil network from a single exemplar. In this manner we obtain an efficient feed-forward one-shot learner, trained end-to-end by minimizing a one-shot classification objective in a learning to learn formulation. In order to make the construction feasible, we propose a number of factorizations of the parameters of the pupil network. We demonstrate encouraging results by learning characters from single exemplars in Omniglot, and by tracking visual objects from a single initial exemplar in the Visual Object Tracking benchmark.

Subfields: 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 Computer Vision and Pattern Recognition

In Representation & Self-Supervised Learning

Citations in the corpus

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].”
HyperNetworks (2016, background): “…with another network is central to the work of (Jaderberg et al., 2016; Andrychowicz et al., 2016), and especially (Denil et al., 2013; Yang et al., 2015; Bertinetto et al., 2016; De Brabandere et al., 2016), where certain parameters in a convolutional network are predicted by another network.”
Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing (2021, neutral): “There are a wide variety of methods to achieve few-shot learning including model agnostic meta-learning [29] (learning features rapidly adaptable to new tasks), embedding learning [8] (embedding each sample in a lower-dimensional space where similar samples are close together), memorybased learning ”
Flamingo: a Visual Language Model for Few-Shot Learning (2022, methodology): “In this paper, we take inspiration from the in-context [11] few-shot learning technique instead of more involved few-shot learning approaches based on metric learning [24, 103, 112, 117] or meta-learning [6, 7, 27, 31, 91, 155].”
CrossTransformers: spatially-aware few-shot transfer (2020, background): “The meta-learner either learns to produce new parameters directly from the new data [9, 33, 56, 62, 64, 72, 73], or learns to produce an update rule to iteratively optimize the base learner to fit the new data [2, 6, 8, 38, 63, 97].”
Meta-learning with differentiable closed-form solvers (2018, methodology): “…learning (Miller et al., 2000; Fei-Fei et al., 2006; Lake et al., 2015; Hariharan & Girshick, 2017) and has recently seen a tremendous surge in interest within the machine learning community (e.g. Vinyals et al. (2016); Bertinetto et al. (2016); Ravi & Larochelle (2017); Finn et al. (2017)).”
Dynamic Neural Networks: A Survey (2021, background): “In addition to computational efficiency, dynamic models have also shown promising results for improving data efficiency in the scenario of few-shot learning [17], [18].”
Billion-scale semi-supervised learning for image classification (2019, background): “Typical works on this line of research propose parameter prediction [4, 33] and data augmentation [12, 14].”
Low-Shot Learning from Imaginary Data (2018, background): “An alternative is to directly predict the classifier weights that would be learned from a large dataset using few novel class examples [2] or from a small dataset classifier [37, 38].”
Deep Meta-Learning: Learning to Learn in the Concept Space (2018, methodology): “Instead of following the typical gradient decent method, (Bertinetto et al., 2016) suggest a feed-forward learner for learning deep neural networks to address the overﬁtting for few-shot learning.”
Bayesian Hypernetworks (2017, background): “A hypernetwork (Ha et al., 2017; Brabandere et al., 2016; Bertinetto et al., 2016) is a neural net that outputs parameters of another neural net (the "primary network") 2 .”
Gradient Episodic Memory for Continual Learning (2017, background): “Zero-shot learning [Lampert et al., 2009, Palatucci et al., 2009] and one-shot learning [Fei-Fei et al., 2003, Vinyals et al., 2016, Santoro et al., 2016, Bertinetto et al., 2016] aim at performing well on unseen tasks, but ignore the catastrophic forgetting of previously learned tasks.”
Continual learning with hypernetworks (2019, background): “…as weight generators, which were originally introduced to dynamically parameterize models in a compressed form (Ha et al., 2017; Schmidhuber, 1992; Bertinetto et al., 2016; Jia et al., 2016). y (2) y (3) f trgt f trgt y (T) f trgt Θ trgt (2) (1) x (2) Θ trgt (3) x (3) Θ trgt ( T ) x ( T ) e (2) e…”
The limits and potentials of deep learning for robotics (2018, methodology): “This class-incremental learning would preferably be data-efﬁcient by using one-shot [13], [60], [92], [99], [124] or low-shot [27], [41], [126] learning techniques.”
Neural Autoregressive Flows (2018, methodology): “Our method increases the expressivity of these previous approaches by using a neural net to output pseudoparameters of another network, thus falling into the hypernetwork framework (Ha et al., 2017; Bertinetto et al., 2016; Jia et al., 2016).”
Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning (2017, background): “This approach has been shown to be effective for achieving zero-shot and one-shot generalization in image classiﬁcation problems (Lei Ba et al., 2015; Bertinetto et al., 2016).”
Large-Scale Long-Tailed Recognition in an Open World (2019, background): “It is often formulated as meta learning [46, 5, 37, 42, 12, 57].”