Search Results for author:
Found 14 papers, 7 papers with code
Open-World Object Manipulation using Pre-trained Vision-Language Models
This brings up a notably difficult challenge for robots: while robot learning approaches allow robots to learn many different behaviors from first-hand experience, it is impractical for robots to have first-hand experiences that span all of this semantic information.
Scaling Robot Learning with Semantically Imagined Experience
Specifically, we make use of the state of the art text-to-image diffusion models and perform aggressive data augmentation on top of our existing robotic manipulation datasets via inpainting various unseen objects for manipulation, backgrounds, and distractors with text guidance.
RT-1: Robotics Transformer for Real-World Control at Scale
By transferring knowledge from large, diverse, task-agnostic datasets, modern machine learning models can solve specific downstream tasks either zero-shot or with small task-specific datasets to a high level of performance.
Self-supervised AutoFlow
Recently, AutoFlow has shown promising results on learning a training set for optical flow, but requires ground truth labels in the target domain to compute its search metric.
Token Turing Machines
We propose Token Turing Machines (TTM), a sequential, autoregressive Transformer model with memory for real-world sequential visual understanding.
Ranked #1 on
Action Detection
on Charades
Open-vocabulary Queryable Scene Representations for Real World Planning
Large language models (LLMs) have unlocked new capabilities of task planning from human instructions.
Simple Open-Vocabulary Object Detection with Vision Transformers
Combining simple architectures with large-scale pre-training has led to massive improvements in image classification.
Ranked #1 on
One-Shot Object Detection
on COCO
Kubric: A scalable dataset generator
Data is the driving force of machine learning, with the amount and quality of training data often being more important for the performance of a system than architecture and training details.
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.
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.
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 #3 on
Optical Flow Estimation
on Sintel Clean unsupervised
Towards Object Detection from Motion
We present a novel approach to weakly supervised object detection.
Teaching Compositionality to CNNs
Convolutional neural networks (CNNs) have shown great success in computer vision, approaching human-level performance when trained for specific tasks via application-specific loss functions.
