Search Results for author:
Found 17 papers, 7 papers with code
Proto-Value Networks: Scaling Representation Learning with Auxiliary Tasks
Combined with a suitable off-policy learning rule, the result is a representation learning algorithm that can be understood as extending Mahadevan & Maggioni (2007)'s proto-value functions to deep reinforcement learning -- accordingly, we call the resulting object proto-value networks.
Learning to Navigate in Complex Environments
Learning to navigate in complex environments with dynamic elements is an important milestone in developing AI agents.
BootsTAP: Bootstrapped Training for Tracking-Any-Point
To endow models with greater understanding of physics and motion, it is useful to enable them to perceive how solid surfaces move and deform in real scenes.
Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples
Few-shot classification refers to learning a classifier for new classes given only a few examples.
Ranked #7 on
Few-Shot Image Classification
on Meta-Dataset Rank
Comparing Transfer and Meta Learning Approaches on a Unified Few-Shot Classification Benchmark
To bridge this gap, we perform a cross-family study of the best transfer and meta learners on both a large-scale meta-learning benchmark (Meta-Dataset, MD), and a transfer learning benchmark (Visual Task Adaptation Benchmark, VTAB).
Efficient Object Localization Using Convolutional Networks
Recent state-of-the-art performance on human-body pose estimation has been achieved with Deep Convolutional Networks (ConvNets).
Ranked #42 on
Pose Estimation
on MPII Human Pose
Stacked What-Where Auto-encoders
The objective function includes reconstruction terms that induce the hidden states in the Deconvnet to be similar to those of the Convnet.
Learning to Linearize Under Uncertainty
Training deep feature hierarchies to solve supervised learning tasks has achieved state of the art performance on many problems in computer vision.
Unsupervised Learning of Spatiotemporally Coherent Metrics
Current state-of-the-art classification and detection algorithms rely on supervised training.
Unsupervised Feature Learning from Temporal Data
Current state-of-the-art classification and detection algorithms rely on supervised training.
An Analysis of Object Representations in Deep Visual Trackers
Despite these strong priors, we show that deep trackers often default to tracking by saliency detection - without relying on the object instance representation.
An Effective Anti-Aliasing Approach for Residual Networks
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.
Impact of Aliasing on Generalization in Deep Convolutional Networks
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 limitations in widely used architectures.
Learned Image Compression for Machine Perception
Compression that ensures high accuracy on computer vision tasks such as image segmentation, classification, and detection therefore has the potential for significant impact across a wide variety of settings.
Inducing Stronger Object Representations in Deep Visual Trackers
Fully convolutional deep correlation networks are integral components of state-of- the-art approaches to single object visual tracking.
Estimating Residential Solar Potential Using Aerial Data
Project Sunroof estimates the solar potential of residential buildings using high quality aerial data.
Course Correcting Koopman Representations
Koopman representations aim to learn features of nonlinear dynamical systems (NLDS) which lead to linear dynamics in the latent space.
