Stochastic Prototype Embeddings

Supervised deep-embedding methods project inputs of a domain to a representational space in which same-class instances lie near one another and different-class instances lie far apart. We propose a probabilistic method that treats embeddings as random variables. Extending a state-of-the-art deterministic method, Prototypical Networks (Snell et al., 2017), our approach supposes the existence of a class prototype around which class instances are Gaussian distributed. The prototype posterior is a product distribution over labeled instances, and query instances are classified by marginalizing relative prototype proximity over embedding uncertainty. We describe an efficient sampler for approximate inference that allows us to train the model at roughly the same space and time cost as its deterministic sibling. Incorporating uncertainty improves performance on few-shot learning and gracefully handles label noise and out-of-distribution inputs. Compared to the state-of-the-art stochastic method, Hedged Instance Embeddings (Oh et al., 2019), we achieve superior large- and open-set classification accuracy. Our method also aligns class-discriminating features with the axes of the embedding space, yielding an interpretable, disentangled representation.

[1]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[2]  Stefanie Jegelka,et al.  Deep Metric Learning via Facility Location , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Sergey Levine,et al.  Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks , 2017, ICML.

[4]  Michael C. Mozer,et al.  Adapted Deep Embeddings: A Synthesis of Methods for k-Shot Inductive Transfer Learning , 2018, NeurIPS.

[5]  Manohar Paluri,et al.  Metric Learning with Adaptive Density Discrimination , 2015, ICLR.

[6]  Chang Huang,et al.  Targeting Ultimate Accuracy: Face Recognition via Deep Embedding , 2015, ArXiv.

[7]  James Philbin,et al.  FaceNet: A unified embedding for face recognition and clustering , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Yann LeCun,et al.  Dimensionality Reduction by Learning an Invariant Mapping , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[9]  Jian Wang,et al.  Deep Metric Learning with Angular Loss , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[10]  Silvio Savarese,et al.  Deep Metric Learning via Lifted Structured Feature Embedding , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Qi Tian,et al.  Scalable Person Re-identification: A Benchmark , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[12]  Michael C. Mozer,et al.  Learning Deep Disentangled Embeddings with the F-Statistic Loss , 2018, NeurIPS.

[13]  Xiaogang Wang,et al.  DeepReID: Deep Filter Pairing Neural Network for Person Re-identification , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[14]  Joshua B. Tenenbaum,et al.  Infinite Mixture Prototypes for Few-Shot Learning , 2019, ICML.

[15]  Richard S. Zemel,et al.  Prototypical Networks for Few-shot Learning , 2017, NIPS.

[16]  Raquel Urtasun,et al.  Few-Shot Learning Through an Information Retrieval Lens , 2017, NIPS.

[17]  Pieter Abbeel,et al.  A Simple Neural Attentive Meta-Learner , 2017, ICLR.

[18]  Seong Joon Oh,et al.  Modeling Uncertainty with Hedged Instance Embedding , 2018, ICLR 2018.

[19]  M. Masson Using confidence intervals for graphically based data interpretation. , 2003, Canadian journal of experimental psychology = Revue canadienne de psychologie experimentale.

[20]  Andrew McCallum,et al.  Word Representations via Gaussian Embedding , 2014, ICLR.

[21]  Stanislav Fort,et al.  Gaussian Prototypical Networks for Few-Shot Learning on Omniglot , 2017, ArXiv.

[22]  Oriol Vinyals,et al.  Matching Networks for One Shot Learning , 2016, NIPS.

[23]  Amos J. Storkey,et al.  Towards a Neural Statistician , 2016, ICLR.

[24]  Joshua B. Tenenbaum,et al.  Human-level concept learning through probabilistic program induction , 2015, Science.

[25]  Victor S. Lempitsky,et al.  Learning Deep Embeddings with Histogram Loss , 2016, NIPS.

[26]  Seong Joon Oh,et al.  Modeling Uncertainty with Hedged Instance Embeddings , 2019, ICLR.

[27]  Shengcai Liao,et al.  Deep Metric Learning for Person Re-identification , 2014, 2014 22nd International Conference on Pattern Recognition.

[28]  Pavlos Protopapas,et al.  Deep Variational Transfer: Transfer Learning through Semi-supervised Deep Generative Models , 2018, ArXiv.

[29]  Serge J. Belongie,et al.  Bayesian representation learning with oracle constraints , 2015, ICLR 2016.

[30]  Yann LeCun,et al.  Learning a similarity metric discriminatively, with application to face verification , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[31]  Gregory R. Koch,et al.  Siamese Neural Networks for One-Shot Image Recognition , 2015 .