1 code implementation • 27 Aug 2020 • Alexander Wang, Mengye Ren, Richard S. Zemel
Sketch drawings capture the salient information of visual concepts.
1 code implementation • ICLR 2021 • Mengye Ren, Michael L. Iuzzolino, Michael C. Mozer, Richard S. Zemel
We aim to bridge the gap between typical human and machine-learning environments by extending the standard framework of few-shot learning to an online, continual setting.
2 code implementations • NeurIPS 2019 • Renjie Liao, Yujia Li, Yang Song, Shenlong Wang, Charlie Nash, William L. Hamilton, David Duvenaud, Raquel Urtasun, Richard S. Zemel
Our model generates graphs one block of nodes and associated edges at a time.
no code implementations • ICLR 2019 • Marc T. Law, Jake Snell, Amir-Massoud Farahmand, Raquel Urtasun, Richard S. Zemel
Most deep learning models rely on expressive high-dimensional representations to achieve good performance on tasks such as classification.
1 code implementation • ICLR 2019 • Renjie Liao, Zhizhen Zhao, Raquel Urtasun, Richard S. Zemel
We propose the Lanczos network (LanczosNet), which uses the Lanczos algorithm to construct low rank approximations of the graph Laplacian for graph convolution.
1 code implementation • NeurIPS 2019 • Mengye Ren, Renjie Liao, Ethan Fetaya, Richard S. Zemel
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.
9 code implementations • ICLR 2018 • Mengye Ren, Eleni Triantafillou, Sachin Ravi, Jake Snell, Kevin Swersky, Joshua B. Tenenbaum, Hugo Larochelle, Richard S. Zemel
To address this paradigm, we propose novel extensions of Prototypical Networks (Snell et al., 2017) that are augmented with the ability to use unlabeled examples when producing prototypes.
no code implementations • ICML 2017 • Marc T. Law, Raquel Urtasun, Richard S. Zemel
We derive a closed-form expression for the gradient that is efficient to compute: the complexity to compute the gradient is linear in the size of the training mini-batch and quadratic in the representation dimensionality.
no code implementations • CVPR 2017 • Marc T. Law, Yao-Liang Yu, Raquel Urtasun, Richard S. Zemel, Eric P. Xing
Classic approaches alternate the optimization over the learned metric and the assignment of similar instances.
42 code implementations • NeurIPS 2017 • Jake Snell, Kevin Swersky, Richard S. Zemel
We propose prototypical networks for the problem of few-shot classification, where a classifier must generalize to new classes not seen in the training set, given only a small number of examples of each new class.
no code implementations • 14 Nov 2016 • Mengye Ren, Renjie Liao, Raquel Urtasun, Fabian H. Sinz, Richard S. Zemel
On the other hand, layer normalization normalizes the activations across all activities within a layer.
1 code implementation • CVPR 2017 • Mengye Ren, Richard S. Zemel
While convolutional neural networks have gained impressive success recently in solving structured prediction problems such as semantic segmentation, it remains a challenge to differentiate individual object instances in the scene.
1 code implementation • 19 Nov 2015 • Jake Snell, Karl Ridgeway, Renjie Liao, Brett D. Roads, Michael C. Mozer, Richard S. Zemel
We propose instead to use a loss function that is better calibrated to human perceptual judgments of image quality: the multiscale structural-similarity score (MS-SSIM).
1 code implementation • 19 Nov 2015 • Yang Song, Alexander G. Schwing, Richard S. Zemel, Raquel Urtasun
Supervised training of deep neural nets typically relies on minimizing cross-entropy.
16 code implementations • NeurIPS 2015 • Ryan Kiros, Yukun Zhu, Ruslan Salakhutdinov, Richard S. Zemel, Antonio Torralba, Raquel Urtasun, Sanja Fidler
The end result is an off-the-shelf encoder that can produce highly generic sentence representations that are robust and perform well in practice.
Ranked #2 on Semantic Similarity on SICK
3 code implementations • 10 Nov 2014 • Ryan Kiros, Ruslan Salakhutdinov, Richard S. Zemel
Inspired by recent advances in multimodal learning and machine translation, we introduce an encoder-decoder pipeline that learns (a): a multimodal joint embedding space with images and text and (b): a novel language model for decoding distributed representations from our space.
no code implementations • NeurIPS 2014 • Ryan Kiros, Richard S. Zemel, Ruslan Salakhutdinov
In this paper we propose a general framework for learning distributed representations of attributes: characteristics of text whose representations can be jointly learned with word embeddings.
1 code implementation • 5 Feb 2014 • Jasper Snoek, Kevin Swersky, Richard S. Zemel, Ryan P. Adams
Bayesian optimization has proven to be a highly effective methodology for the global optimization of unknown, expensive and multimodal functions.
no code implementations • NeurIPS 2012 • Maksims Volkovs, Richard S. Zemel
The primary application of collaborate filtering (CF) is to recommend a small set of items to a user, which entails ranking.
no code implementations • NeurIPS 2012 • Maksims Volkovs, Richard S. Zemel
Bipartite matching problems characterize many situations, ranging from ranking in information retrieval to correspondence in vision.
no code implementations • NeurIPS 2012 • Kevin Swersky, Ilya Sutskever, Daniel Tarlow, Richard S. Zemel, Ruslan R. Salakhutdinov, Ryan P. Adams
The Restricted Boltzmann Machine (RBM) is a popular density model that is also good for extracting features.
1 code implementation • 20 Jun 2012 • Benjamin Marlin, Richard S. Zemel, Sam Roweis, Malcolm Slaney
Rating prediction is an important application, and a popular research topic in collaborative filtering.
no code implementations • 9 Jun 2011 • Ryan Prescott Adams, Richard S. Zemel
It is of increasing importance to develop learning methods for ranking.
no code implementations • NeurIPS 2008 • Xuming He, Richard S. Zemel
Extensive labeled data for image annotation systems, which learn to assign class labels to image regions, is difficult to obtain.