Search Results for author:
Found 9 papers, 5 papers with code
Align-to-Distill: Trainable Attention Alignment for Knowledge Distillation in Neural Machine Translation
The Attention Alignment Module in A2D performs a dense head-by-head comparison between student and teacher attention heads across layers, turning the combinatorial mapping heuristics into a learning problem.
Predict to Detect: Prediction-guided 3D Object Detection using Sequential Images
To address this limitation, we propose a novel 3D object detection model, P2D (Predict to Detect), that integrates a prediction scheme into a detection framework to explicitly extract and leverage motion features.
CRN: Camera Radar Net for Accurate, Robust, Efficient 3D Perception
Autonomous driving requires an accurate and fast 3D perception system that includes 3D object detection, tracking, and segmentation.
Ranked #2 on
3D Multi-Object Tracking
on nuscenes Camera-Radar
UpCycling: Semi-supervised 3D Object Detection without Sharing Raw-level Unlabeled Scenes
In this paper, we propose UpCycling, a novel SSL framework for 3D object detection with zero additional raw-level point cloud: learning from unlabeled de-identified intermediate features (i. e., smashed data) to preserve privacy.
Boosting Monocular 3D Object Detection with Object-Centric Auxiliary Depth Supervision
In this way, our 3D detection network can be supervised by more depth supervision from raw LiDAR points, which does not require any human annotation cost, to estimate accurate depth without explicitly predicting the depth map.
CRAFT: Camera-Radar 3D Object Detection with Spatio-Contextual Fusion Transformer
Camera and radar sensors have significant advantages in cost, reliability, and maintenance compared to LiDAR.
Ranked #6 on
3D Object Detection
on nuscenes Camera-Radar
A flexible empirical Bayes approach to multiple linear regression and connections with penalized regression
We introduce a new empirical Bayes approach for large-scale multiple linear regression.
Scale Invariant Power Iteration
In this work, we introduce a new class of optimization problems called scale invariant problems and prove that they can be efficiently solved by scale invariant power iteration (SCI-PI) with a generalized convergence guarantee of power iteration.
A fast algorithm for maximum likelihood estimation of mixture proportions using sequential quadratic programming
It is substantially faster than the interior point method, and just as accurate.
Computation Methodology
