Search Results for author:
Found 25 papers, 9 papers with code
Linear Transformer Topological Masking with Graph Random Features
When training transformers on graph-structured data, incorporating information about the underlying topology is crucial for good performance.
Imitating Language via Scalable Inverse Reinforcement Learning
We focus on investigating the inverse reinforcement learning (IRL) perspective to imitation, extracting rewards and directly optimizing sequences instead of individual token likelihoods and evaluate its benefits for fine-tuning large language models.
Robots That Can See: Leveraging Human Pose for Trajectory Prediction
Anticipating the motion of all humans in dynamic environments such as homes and offices is critical to enable safe and effective robot navigation.
Robotic Table Tennis: A Case Study into a High Speed Learning System
We present a deep-dive into a real-world robotic learning system that, in previous work, was shown to be capable of hundreds of table tennis rallies with a human and has the ability to precisely return the ball to desired targets.
Video OWL-ViT: Temporally-consistent open-world localization in video
Our model is end-to-end trainable on video data and enjoys improved temporal consistency compared to tracking-by-detection baselines, while retaining the open-world capabilities of the backbone detector.
Scene Transformer: A unified architecture for predicting future trajectories of multiple agents
In this work, we formulate a model for predicting the behavior of all agents jointly, producing consistent futures that account for interactions between agents.
RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detection
These larger detection ranges require more efficient and accurate detection models.
Scene Transformer: A unified architecture for predicting multiple agent trajectories
In this work, we formulate a model for predicting the behavior of all agents jointly, producing consistent futures that account for interactions between agents.
Local Metrics for Multi-Object Tracking
This paper introduces temporally local metrics for Multi-Object Tracking.
Range Conditioned Dilated Convolutions for Scale Invariant 3D Object Detection
This paper presents a novel 3D object detection framework that processes LiDAR data directly on its native representation: range images.
Guiding Physical Intuition with Neural Stethoscopes
Using an adversarial stethoscope, the network is successfully de-biased, leading to a performance increase from 66% to 88%.
Learning to Drive from Simulation without Real World Labels
Simulation can be a powerful tool for understanding machine learning systems and designing methods to solve real-world problems.
Deep Cosine Metric Learning for Person Re-Identification
Metric learning aims to construct an embedding where two extracted features corresponding to the same identity are likely to be closer than features from different identities.
Dropout Distillation for Efficiently Estimating Model Confidence
We also propose better calibration within the state of the art Faster R-CNN object detection framework and show, using the COCO dataset, that DDN helps train better calibrated object detectors.
Learning to Drive in a Day
We demonstrate the first application of deep reinforcement learning to autonomous driving.
Scrutinizing and De-Biasing Intuitive Physics with Neural Stethoscopes
Conversely, training on an easy dataset where visual cues are positively correlated with stability, the baseline model learns a bias leading to poor performance on a harder dataset.
Meshed Up: Learnt Error Correction in 3D Reconstructions
We train a suitably deep network architecture with two 3D meshes: a high-quality laser reconstruction, and a lower quality stereo image reconstruction.
Incremental Adversarial Domain Adaptation for Continually Changing Environments
Continuous appearance shifts such as changes in weather and lighting conditions can impact the performance of deployed machine learning models.
Generative Adversarial Network
Unsupervised Domain Adaptation
What Makes a Place? Building Bespoke Place Dependent Object Detectors for Robotics
This paper is about enabling robots to improve their perceptual performance through repeated use in their operating environment, creating local expert detectors fitted to the places through which a robot moves.
Hierarchical Attentive Recurrent Tracking
Class-agnostic object tracking is particularly difficult in cluttered environments as target specific discriminative models cannot be learned a priori.
Simple Online and Realtime Tracking with a Deep Association Metric
Simple Online and Realtime Tracking (SORT) is a pragmatic approach to multiple object tracking with a focus on simple, effective algorithms.
Ranked #3 on
3D Multi-Object Tracking
on Waymo Open Dataset
3D Multi-Object Tracking
Large-Scale Person Re-Identification
+2
Addressing Appearance Change in Outdoor Robotics with Adversarial Domain Adaptation
Appearance changes due to weather and seasonal conditions represent a strong impediment to the robust implementation of machine learning systems in outdoor robotics.
Simple Online and Realtime Tracking
This paper explores a pragmatic approach to multiple object tracking where the main focus is to associate objects efficiently for online and realtime applications.
Ranked #2 on
Multi-Object Tracking
on MOT15
Fine-Grained Classification via Mixture of Deep Convolutional Neural Networks
We present a novel deep convolutional neural network (DCNN) system for fine-grained image classification, called a mixture of DCNNs (MixDCNN).
