Search Results for author:
Found 13 papers, 8 papers with code
Better Monocular 3D Detectors with LiDAR from the Past
Accurate 3D object detection is crucial to autonomous driving.
Remote Sensing Vision-Language Foundation Models without Annotations via Ground Remote Alignment
We introduce a method to train vision-language models for remote-sensing images without using any textual annotations.
Pre-Training LiDAR-Based 3D Object Detectors Through Colorization
Accurate 3D object detection and understanding for self-driving cars heavily relies on LiDAR point clouds, necessitating large amounts of labeled data to train.
Unsupervised Domain Adaptation for Self-Driving from Past Traversal Features
Additionally, we leverage the statistics for a novel self-training process to stabilize the training.
Emergent Correspondence from Image Diffusion
We propose a simple strategy to extract this implicit knowledge out of diffusion networks as image features, namely DIffusion FeaTures (DIFT), and use them to establish correspondences between real images.
Distilling from Similar Tasks for Transfer Learning on a Budget
To alleviate this, we propose a weighted multi-source distillation method to distill multiple source models trained on different domains weighted by their relevance for the target task into a single efficient model (named DistillWeighted).
Unsupervised Adaptation from Repeated Traversals for Autonomous Driving
For a self-driving car to operate reliably, its perceptual system must generalize to the end-user's environment -- ideally without additional annotation efforts.
Learning to Detect Mobile Objects from LiDAR Scans Without Labels
Current 3D object detectors for autonomous driving are almost entirely trained on human-annotated data.
Task2Sim: Towards Effective Pre-Training and Transfer From Synthetic Data
It is thus better to tailor synthetic pre-training data to a specific downstream task, for best performance.
Task2Sim : Towards Effective Pre-training and Transfer from Synthetic Data
It is thus better to tailor synthetic pre-training data to a specific downstream task, for best performance.
A theoretically grounded characterization of feature representations
We present theoretical results showing how these measurements can be used to bound the error of the downstream classifiers, and show empirically that these bounds correlate well with actual downstream performance.
Coarsely-Labeled Data for Better Few-Shot Transfer
Few-shot learning is based on the premise that labels are expensive, especially when they are fine-grained and require expertise.
Self-training for Few-shot Transfer Across Extreme Task Differences
Most few-shot learning techniques are pre-trained on a large, labeled "base dataset".
