Timezone: »
Machine learning classifiers are often trained to recognize a set of pre-defined classes. However, in many applications, it is often desirable to have the flexibility of learning additional concepts, with limited data and without re-training on the full training set. This paper addresses this problem, incremental few-shot learning, where a regular classification network has already been trained to recognize a set of base classes, and several extra novel classes are being considered, each with only a few labeled examples. After learning the novel classes, the model is then evaluated on the overall classification performance on both base and novel classes. To this end, we propose a meta-learning model, the Attention Attractor Network, which regularizes the learning of novel classes. In each episode, we train a set of new weights to recognize novel classes until they converge, and we show that the technique of recurrent back-propagation can back-propagate through the optimization process and facilitate the learning of these parameters. We demonstrate that the learned attractor network can help recognize novel classes while remembering old classes without the need to review the original training set, outperforming various baselines.
Author Information
Mengye Ren (University of Toronto / Uber ATG)
Renjie Liao (University of Toronto)
Ethan Fetaya (Bar Ilan University)
Richard Zemel (Vector Institute/University of Toronto)
More from the Same Authors
-
2020 Poster: LoCo: Local Contrastive Representation Learning »
Yuwen Xiong · Mengye Ren · Raquel Urtasun -
2019 Workshop: Graph Representation Learning »
Will Hamilton · Rianne van den Berg · Michael Bronstein · Stefanie Jegelka · Thomas Kipf · Jure Leskovec · Renjie Liao · Yizhou Sun · Petar Veličković -
2019 Poster: SMILe: Scalable Meta Inverse Reinforcement Learning through Context-Conditional Policies »
Seyed Kamyar Seyed Ghasemipour · Shixiang (Shane) Gu · Richard Zemel -
2019 Poster: Efficient Graph Generation with Graph Recurrent Attention Networks »
Renjie Liao · Yujia Li · Yang Song · Shenlong Wang · Will Hamilton · David Duvenaud · Raquel Urtasun · Richard Zemel -
2018 Poster: Learning Latent Subspaces in Variational Autoencoders »
Jack Klys · Jake Snell · Richard Zemel -
2018 Poster: Predict Responsibly: Improving Fairness and Accuracy by Learning to Defer »
David Madras · Toni Pitassi · Richard Zemel -
2018 Poster: Neural Guided Constraint Logic Programming for Program Synthesis »
Lisa Zhang · Gregory Rosenblatt · Ethan Fetaya · Renjie Liao · William Byrd · Matthew Might · Raquel Urtasun · Richard Zemel -
2017 Poster: Dualing GANs »
Yujia Li · Alexander Schwing · Kuan-Chieh Wang · Richard Zemel -
2017 Poster: Causal Effect Inference with Deep Latent-Variable Models »
Christos Louizos · Uri Shalit · Joris M Mooij · David Sontag · Richard Zemel · Max Welling -
2017 Spotlight: Dualing GANs »
Yujia Li · Alexander Schwing · Kuan-Chieh Wang · Richard Zemel -
2017 Poster: The Reversible Residual Network: Backpropagation Without Storing Activations »
Aidan Gomez · Mengye Ren · Raquel Urtasun · Roger Grosse -
2017 Poster: Few-Shot Learning Through an Information Retrieval Lens »
Eleni Triantafillou · Richard Zemel · Raquel Urtasun -
2017 Poster: Prototypical Networks for Few-shot Learning »
Jake Snell · Kevin Swersky · Richard Zemel -
2016 Poster: Understanding the Effective Receptive Field in Deep Convolutional Neural Networks »
Wenjie Luo · Yujia Li · Raquel Urtasun · Richard Zemel -
2016 Poster: Learning Deep Parsimonious Representations »
Renjie Liao · Alex Schwing · Richard Zemel · Raquel Urtasun -
2015 Poster: Skip-Thought Vectors »
Jamie Kiros · Yukun Zhu · Russ Salakhutdinov · Richard Zemel · Raquel Urtasun · Antonio Torralba · Sanja Fidler -
2015 Poster: Exploring Models and Data for Image Question Answering »
Mengye Ren · Jamie Kiros · Richard Zemel -
2014 Workshop: Representation and Learning Methods for Complex Outputs »
Richard Zemel · Dale Schuurmans · Kilian Q Weinberger · Yuhong Guo · Jia Deng · Francesco Dinuzzo · Hal Daumé III · Honglak Lee · Noah A Smith · Richard Sutton · Jiaqian YU · Vitaly Kuznetsov · Luke Vilnis · Hanchen Xiong · Calvin Murdock · Thomas Unterthiner · Jean-Francis Roy · Martin Renqiang Min · Hichem SAHBI · Fabio Massimo Zanzotto -
2014 Poster: A Multiplicative Model for Learning Distributed Text-Based Attribute Representations »
Jamie Kiros · Richard Zemel · Russ Salakhutdinov -
2013 Workshop: Output Representation Learning »
Yuhong Guo · Dale Schuurmans · Richard Zemel · Samy Bengio · Yoshua Bengio · Li Deng · Dan Roth · Kilian Q Weinberger · Jason Weston · Kihyuk Sohn · Florent Perronnin · Gabriel Synnaeve · Pablo R Strasser · julien audiffren · Carlo Ciliberto · Dan Goldwasser -
2013 Poster: A Determinantal Point Process Latent Variable Model for Inhibition in Neural Spiking Data »
Jasper Snoek · Richard Zemel · Ryan Adams -
2013 Poster: On the Expressive Power of Restricted Boltzmann Machines »
James Martens · Arkadev Chattopadhya · Toni Pitassi · Richard Zemel -
2012 Poster: Collaborative Ranking With 17 Parameters »
Maksims Volkovs · Richard Zemel -
2012 Poster: Bayesian n-Choose-k Models for Classification and Ranking »
Kevin Swersky · Daniel Tarlow · Richard Zemel · Ryan Adams · Brendan J Frey -
2012 Poster: Efficient Sampling for Bipartite Matching Problems »
Maksims Volkovs · Richard Zemel -
2012 Poster: Cardinality Restricted Boltzmann Machines »
Kevin Swersky · Daniel Tarlow · Ilya Sutskever · Richard Zemel · Russ Salakhutdinov · Ryan Adams -
2010 Talk: Opening Remarks and Awards »
Richard Zemel · Terrence Sejnowski · John Shawe-Taylor -
2009 Placeholder: Opening Remarks »
Richard Zemel -
2008 Poster: Comparing model predictions of response bias and variance in cue combination »
Rama Natarajan · Iain Murray · Ladan Shams · Richard Zemel -
2008 Poster: Learning Hybrid Models for Image Annotation with Partially Labeled Data »
Xuming He · Richard Zemel -
2008 Poster: Competing RBM density models for classification of fMRI images »
Tanya Schmah · Geoffrey E Hinton · Richard Zemel