Search Results for author:
Found 16 papers, 8 papers with code
Conditional Object-Centric Learning from Video
Object-centric representations are a promising path toward more systematic generalization by providing flexible abstractions upon which compositional world models can be built.
SMURF: Self-Teaching Multi-Frame Unsupervised RAFT with Full-Image Warping
We present SMURF, a method for unsupervised learning of optical flow that improves state of the art on all benchmarks by $36\%$ to $40\%$ (over the prior best method UFlow) and even outperforms several supervised approaches such as PWC-Net and FlowNet2.
MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale
In this paper, we study how a large-scale collective robotic learning system can acquire a repertoire of behaviors simultaneously, sharing exploration, experience, and representations across tasks.
Adaptive Intermediate Representations for Video Understanding
A common strategy to video understanding is to incorporate spatial and motion information by fusing features derived from RGB frames and optical flow.
Ranked #5 on
Action Classification
on Toyota Smarthome dataset
The Distracting Control Suite -- A Challenging Benchmark for Reinforcement Learning from Pixels
Our experiments show that current RL methods for vision-based control perform poorly under distractions, and that their performance decreases with increasing distraction complexity, showing that new methods are needed to cope with the visual complexities of the real world.
Learning Object-Centric Video Models by Contrasting Sets
We address this problem by introducing a global, set-based contrastive loss: instead of contrasting individual slot representations against one another, we aggregate the representations and contrast the joined sets against one another.
A Geometric Perspective on Self-Supervised Policy Adaptation
One of the most challenging aspects of real-world reinforcement learning (RL) is the multitude of unpredictable and ever-changing distractions that could divert an agent from what was tasked to do in its training environment.
What Matters in Unsupervised Optical Flow
We systematically compare and analyze a set of key components in unsupervised optical flow to identify which photometric loss, occlusion handling, and smoothness regularization is most effective.
Ranked #5 on
Optical Flow Estimation
on Sintel Clean unsupervised
Differentiable Mapping Networks: Learning Structured Map Representations for Sparse Visual Localization
We address these tasks by combining spatial structure (differentiable mapping) and end-to-end learning in a novel neural network architecture: the Differentiable Mapping Network (DMN).
Towards Differentiable Resampling
Resampling is a key component of sample-based recursive state estimation in particle filters.
KeyPose: Multi-View 3D Labeling and Keypoint Estimation for Transparent Objects
We address two problems: first, we establish an easy method for capturing and labeling 3D keypoints on desktop objects with an RGB camera; and second, we develop a deep neural network, called $KeyPose$, that learns to accurately predict object poses using 3D keypoints, from stereo input, and works even for transparent objects.
Towards Object Detection from Motion
We present a novel approach to weakly supervised object detection.
Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Cameras
We present a novel method for simultaneous learning of depth, egomotion, object motion, and camera intrinsics from monocular videos, using only consistency across neighboring video frames as supervision signal.
Ranked #11 on
Unsupervised Monocular Depth Estimation
on Cityscapes
Differentiable Particle Filters: End-to-End Learning with Algorithmic Priors
We present differentiable particle filters (DPFs): a differentiable implementation of the particle filter algorithm with learnable motion and measurement models.
PVEs: Position-Velocity Encoders for Unsupervised Learning of Structured State Representations
We propose position-velocity encoders (PVEs) which learn---without supervision---to encode images to positions and velocities of task-relevant objects.
Patterns for Learning with Side Information
Supervised, semi-supervised, and unsupervised learning estimate a function given input/output samples.
