Search Results for author:
Found 8 papers, 3 papers with code
UOR: Universal Backdoor Attacks on Pre-trained Language Models
In this paper, we first summarize the requirements that a more threatening backdoor attack against PLMs should satisfy, and then propose a new backdoor attack method called UOR, which breaks the bottleneck of the previous approach by turning manual selection into automatic optimization.
Millimeter-level Resolution Photonic Multiband Radar Using a Single MZM and Sub-GHz-Bandwidth Electronics
We here propose a novel cost-effective millimeter-level resolution photonic multiband radar system using a single MZM driven by a 1-GHz-bandwidth LFM signal.
Cost-effective photonic super-resolution millimeter-wave joint radar-communication system using self-coherent detection
Then the self-coherent detection, as a simple and low-cost means, is accordingly facilitated for both de-chirping of MMW radar and frequency down-conversion reception of MMW communication, which circumvents the costly high-speed mixers along with MMW local oscillators and more significantly achieves the real-time decomposition of radar and communication information.
FedPrompt: Communication-Efficient and Privacy Preserving Prompt Tuning in Federated Learning
In this paper, we propose "FedPrompt" to study prompt tuning in a model split aggregation way using FL, and prove that split aggregation greatly reduces the communication cost, only 0. 01% of the PLMs' parameters, with little decrease on accuracy both on IID and Non-IID data distribution.
Time3D: End-to-End Joint Monocular 3D Object Detection and Tracking for Autonomous Driving
While separately leveraging monocular 3D object detection and 2D multi-object tracking can be straightforwardly applied to sequence images in a frame-by-frame fashion, stand-alone tracker cuts off the transmission of the uncertainty from the 3D detector to tracking while cannot pass tracking error differentials back to the 3D detector.
RTS3D: Real-time Stereo 3D Detection from 4D Feature-Consistency Embedding Space for Autonomous Driving
Different from the 3D occupancy space in the Pseudo-LiDAR similar methods, we design a novel 4D feature-consistent embedding (FCE) space as the intermediate representation of the 3D scene without depth supervision.
Monocular 3D Detection with Geometric Constraints Embedding and Semi-supervised Training
In this work, we propose a novel single-shot and keypoints-based framework for monocular 3D objects detection using only RGB images, called KM3D-Net.
RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving
Different from these approaches, our method predicts the nine perspective keypoints of a 3D bounding box in image space, and then utilize the geometric relationship of 3D and 2D perspectives to recover the dimension, location, and orientation in 3D space.
Ranked #6 on
Vehicle Pose Estimation
on KITTI Cars Hard
