Search Results for author: Xiaohua LI

Found 10 papers, 2 papers with code

Dimension Reduction for Efficient Dense Retrieval via Conditional Autoencoder

1 code implementation6 May 2022 Zhenghao Liu, Han Zhang, Chenyan Xiong, Zhiyuan Liu, Yu Gu, Xiaohua LI

To reduce the embedding dimensions of dense retrieval, this paper proposes a Conditional Autoencoder (ConAE) to compress the high-dimensional embeddings to maintain the same embedding distribution and better recover the ranking features.

Dimensionality Reduction Information Retrieval

Mitigating Black-Box Adversarial Attacks via Output Noise Perturbation

no code implementations30 Sep 2021 Manjushree B. Aithal, Xiaohua LI

In this paper, we study the method of adding white noise to the DNN output to mitigate such attacks, with a unique focus on the trade-off analysis of noise level and query cost.

TPPI-Net: Towards Efficient and Practical Hyperspectral Image Classification

no code implementations18 Mar 2021 Hao Chen, Xiaohua LI, Jiliu Zhou

Hyperspectral Image(HSI) classification is the most vibrant field of research in the hyperspectral community, which aims to assign each pixel in the image to one certain category based on its spectral-spatial characteristics.

Classification General Classification +1

A Spike Learning System for Event-driven Object Recognition

no code implementations21 Jan 2021 Shibo Zhou, Wei Wang, Xiaohua LI, Zhanpeng Jin

The proposed temporal coding scheme maps each event's arrival time and data into SNN spike time so that asynchronously-arrived events are processed immediately without delay.

Object Recognition

Spiking Neural Networks with Single-Spike Temporal-Coded Neurons for Network Intrusion Detection

no code implementations15 Oct 2020 Shibo Zhou, Xiaohua LI

To support this claim, we show that SNNs built with nonleaky neurons can have a less-complex and less-nonlinear input-output response.

Network Intrusion Detection

Deep SCNN-based Real-time Object Detection for Self-driving Vehicles Using LiDAR Temporal Data

no code implementations17 Dec 2019 Shibo Zhou, Ying Chen, Xiaohua LI, Arindam Sanyal

In this paper, we integrate spiking convolutional neural network (SCNN) with temporal coding into the YOLOv2 architecture for real-time object detection.

3D Object Detection Real-Time Object Detection +1

Temporal-Coded Deep Spiking Neural Network with Easy Training and Robust Performance

1 code implementation24 Sep 2019 Shibo Zhou, Xiaohua LI, Ying Chen, Sanjeev T. Chandrasekaran, Arindam Sanyal

Spiking neural network (SNN) is interesting both theoretically and practically because of its strong bio-inspiration nature and potentially outstanding energy efficiency.

Data Augmentation Object Recognition

Who is Smarter? Intelligence Measure of Learning-based Cognitive Radios

no code implementations26 Dec 2017 Monireh Dabaghchian, Amir Alipour-Fanid, Songsong Liu, Kai Zeng, Xiaohua LI, Yu Chen

Then we apply factor analysis on the performance data to identify and quantize the intelligence factors and cognitive capabilities of the CR.

Cannot find the paper you are looking for? You can Submit a new open access paper.