367 citations · 798 across the 13 of their papers we have counts for
14 papers
Block-State Transformers
Mahan Fathi, Jonathan Pilault, Orhan Firat +3
State space models (SSMs) have shown impressive results on tasks that require modeling long-range dependencies and efficiently scale to long sequences owing to their subquadratic r…
Proto-Value Networks: Scaling Representation Learning with Auxiliary Tasks
Jesse Farebrother, Joshua Greaves, Rishabh Agarwal +4
Auxiliary tasks improve the representations learned by deep reinforcement learning agents. Analytically, their effect is reasonably well understood; in practice, however, their pri…
Learned Image Compression for Machine Perception
Felipe Codevilla, Jean Gabriel Simard, Ross Goroshin +1
Recent work has shown that learned image compression strategies can outperform standard hand-crafted compression algorithms that have been developed over decades of intensive resea…
Impact of Aliasing on Generalization in Deep Convolutional Networks
Cristina Vasconcelos, Hugo Larochelle, Vincent Dumoulin +3
We investigate the impact of aliasing on generalization in Deep Convolutional Networks and show that data augmentation schemes alone are unable to prevent it due to structural limi…
Comparing Transfer and Meta Learning Approaches on a Unified Few-Shot Classification Benchmark
Vincent Dumoulin, Neil Houlsby, Utku Evci +4
Meta and transfer learning are two successful families of approaches to few-shot learning. Despite highly related goals, state-of-the-art advances in each family are measured large…
An Effective Anti-Aliasing Approach for Residual Networks
Cristina Vasconcelos, Hugo Larochelle, Vincent Dumoulin +2
Image pre-processing in the frequency domain has traditionally played a vital role in computer vision and was even part of the standard pipeline in the early days of deep learning.…
An Analysis of Object Representations in Deep Visual Trackers
Ross Goroshin, Jonathan Tompson, Debidatta Dwibedi
Fully convolutional deep correlation networks are integral components of state-of the-art approaches to single object visual tracking. It is commonly assumed that these networks pe…
Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples
Eleni Triantafillou, Tyler Zhu, Vincent Dumoulin +8
Few-shot classification refers to learning a classifier for new classes given only a few examples. While a plethora of models have emerged to tackle it, we find the procedure and d…
Learning to Navigate in Complex Environments
Piotr Mirowski, Razvan Pascanu, Fabio Viola +9
Learning to navigate in complex environments with dynamic elements is an important milestone in developing AI agents. In this work we formulate the navigation question as a reinfor…
Learning to Linearize Under Uncertainty
Ross Goroshin, Michael Mathieu, Yann LeCun
Training deep feature hierarchies to solve supervised learning tasks has achieved state of the art performance on many problems in computer vision. However, a principled way in whi…
Stacked What-Where Auto-encoders
Junbo Zhao, Michael Mathieu, Ross Goroshin +1
We present a novel architecture, the "stacked what-where auto-encoders" (SWWAE), which integrates discriminative and generative pathways and provides a unified approach to supervis…
Unsupervised Feature Learning from Temporal Data
Ross Goroshin, Joan Bruna, Jonathan Tompson +2
Current state-of-the-art classification and detection algorithms rely on supervised training. In this work we study unsupervised feature learning in the context of temporally coher…
Unsupervised Learning of Spatiotemporally Coherent Metrics
Ross Goroshin, Joan Bruna, Jonathan Tompson +2
Current state-of-the-art classification and detection algorithms rely on supervised training. In this work we study unsupervised feature learning in the context of temporally coher…
Efficient Object Localization Using Convolutional Networks
Jonathan Tompson, Ross Goroshin, Arjun Jain +2
Recent state-of-the-art performance on human-body pose estimation has been achieved with Deep Convolutional Networks (ConvNets). Traditional ConvNet architectures include pooling a…