Fast Adaptation in Generative Models with Generative Matching Networks

Bartunov, Sergey; Vetrov, Dmitry P.

doi:10.48550/arxiv.1612.02192

Cited by 7 publications

(10 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CVAEs have been extended in a number of ways for example by adding attention (Rezende et al, 2016). Another related extension is generative matching networks (GMNs, Bartunov & Vetrov (2016)), where the conditioning input is pre-processed in a way that is similar to the matching networks model.…”

Section: Conditional Latent Variable Modelsmentioning

confidence: 99%

Neural Processes

Garnelo¹,

Schwarz²,

Rosenbaum³

et al. 2018

Preprint

101

226

View full text Add to dashboard Cite

A neural network (NN) is a parameterised function that can be tuned via gradient descent to approximate a labelled collection of data with high precision. A Gaussian process (GP), on the other hand, is a probabilistic model that defines a distribution over possible functions, and is updated in light of data via the rules of probabilistic inference. GPs are probabilistic, data-efficient and flexible, however they are also computationally intensive and thus limited in their applicability. We introduce a class of neural latent variable models which we call Neural Processes (NPs), combining the best of both worlds. Like GPs, NPs define distributions over functions, are capable of rapid adaptation to new observations, and can estimate the uncertainty in their predictions. Like NNs, NPs are computationally efficient during training and evaluation but also learn to adapt their priors to data. We demonstrate the performance of NPs on a range of learning tasks, including regression and optimisation, and compare and contrast with related models in the literature.

show abstract

Section: Conditional Latent Variable Modelsmentioning

confidence: 99%

Neural Processes

Garnelo¹,

Schwarz²,

Rosenbaum³

et al. 2018

Preprint

101

226

View full text Add to dashboard Cite

show abstract

“…4a for an illustration of the training and testing phases of RTCoHand framework. Our idea of solving adaptation via conditional prediction is partially inspired by the line of research on NPs [11], [12], [13] and conceptually similar to few-shot learning, where the target data is compared to observed data in some feature space [24], [25], [26], [27]. For more detailed analysis of such connection, we refer readers to [11], [12], [13].…”

Section: Rtcohand Framework In Cobot Perspectivementioning

confidence: 99%

Learn from Human Teams: a Probabilistic Solution to Real-Time Collaborative Robot Handling with Dynamic Gesture Commands

Chen¹,

Alvin²,

Liu³

2021

Preprint

View full text Add to dashboard Cite

We study real-time collaborative robot (cobot) handling, where the cobot maneuvers a workpiece under human commands. This is useful when it is risky for humans to directly handle the workpiece. However, it is hard to make the cobot both easy to command and flexible in possible operations. In this work, we propose a Real-Time Collaborative Robot Handling (RTCoHand) framework that allows the control of cobot via user-customized dynamic gestures. This is hard due to variations among users, human motion uncertainties, and noisy human input. We model the task as a probabilistic generative process, referred to as Conditional Collaborative Handling Process (CCHP), and learn from human-human collaboration. We thoroughly evaluate the adaptability and robustness of CCHP and apply our approach to a real-time cobot handling task with Kinova Gen3 robot arm. We achieve seamless human-robot collaboration with both experienced and new users. Compared to classical controllers, RTCoHand allows significantly more complex maneuvers and lower user cognitive burden. It also eliminates the need for trialand-error, rendering it advantageous in safety-critical tasks.

show abstract

“…Most recently, a few works [28,41] shift the attention to few-shot from discriminative to generative tasks, especially based on GANs. Some works focus on few-shot density estimation based on matching networks [1], sequential generative models [32], or autoregressive models [31] but they are limited to generating simple patterns and low resolution results. The work of [28,41] showed first promising high resolution results on complex natural images given the recent success in high-quality GAN training.…”

Section: Related Workmentioning

confidence: 99%

Few-shot Image Generation with Elastic Weight Consolidation

Li,

Zhang,

et al. 2020

Preprint

View full text Add to dashboard Cite

Few-shot image generation seeks to generate more data of a given domain, with only few available training examples. As it is unreasonable to expect to fully infer the distribution from just a few observations (e.g., emojis), we seek to leverage a large, related source domain as pretraining (e.g., human faces). Thus, we wish to preserve the diversity of the source domain, while adapting to the appearance of the target. We adapt a pretrained model, without introducing any additional parameters, to the few examples of the target domain. Crucially, we regularize the changes of the weights during this adaptation, in order to best preserve the "information" of the source dataset, while fitting the target. We demonstrate the effectiveness of our algorithm by generating high-quality results of different target domains, including those with extremely few examples (e.g., ≤10). We also analyze the performance of our method with respect to some important factors, such as the number of examples and the dissimilarity between the source and target domain.

show abstract

Fast Adaptation in Generative Models with Generative Matching Networks

Cited by 7 publications

References 18 publications

Neural Processes

Neural Processes

Learn from Human Teams: a Probabilistic Solution to Real-Time Collaborative Robot Handling with Dynamic Gesture Commands

Few-shot Image Generation with Elastic Weight Consolidation

Contact Info

Product

Resources

About