Search Results for author: Pu Li

Found 14 papers, 5 papers with code

Group channel pruning and spatial attention distilling for object detection

1 code implementation2 Jun 2023 Yun Chu, Pu Li, Yong Bai, Zhuhua Hu, Yongqing Chen, Jiafeng Lu

To address these issues, for the object detection network we introduce a three-stage model compression method: dynamic sparse training, group channel pruning, and spatial attention distilling.

Knowledge Distillation Model Compression +3

RAPQ: Rescuing Accuracy for Power-of-Two Low-bit Post-training Quantization

1 code implementation26 Apr 2022 Hongyi Yao, Pu Li, Jian Cao, Xiangcheng Liu, Chenying Xie, Bingzhang Wang

We are the first to propose the more constrained but hardware-friendly Power-of-Two quantization scheme for low-bit PTQ specially and prove that it can achieve nearly the same accuracy as SOTA PTQ method.

Quantization

Learning Knowledge-Rich Sequential Model for Planar Homography Estimation in Aerial Video

1 code implementation5 Apr 2023 Pu Li, Xiaobai Liu

To address this concern, we develop a sequential estimator that directly processes a sequence of video frames and estimates their pairwise planar homographic transformations in batches.

Homography Estimation

Learning Stage-wise GANs for Whistle Extraction in Time-Frequency Spectrograms

1 code implementation5 Apr 2023 Pu Li, Marie Roch, Holger Klinck, Erica Fleishman, Douglas Gillespie, Eva-Marie Nosal, Yu Shiu, Xiaobai Liu

To overcome this limitation, we present a framework of stage-wise generative adversarial networks (GANs), which compile new whistle data suitable for deep model training via three stages: generation of background noise in the spectrogram, generation of whistle contours, and generation of whistle signals.

Data Augmentation

Review of Text Style Transfer Based on Deep Learning

no code implementations6 May 2020 Xiang-Yang Li, Guo Pu, Keyu Ming, Pu Li, Jie Wang, Yuxuan Wang

In the traditional text style transfer model, the text style is generally relied on by experts knowledge and hand-designed rules, but with the application of deep learning in the field of natural language processing, the text style transfer method based on deep learning Started to be heavily researched.

Style Transfer Text Style Transfer

Fabry-Perot Lasers as Enablers for Parallel Reservoir Computing

no code implementations4 May 2020 Adonis Bogris, Charis Mesaritakis, Stavros Deligiannidis, Pu Li

We introduce the use of Fabry-Perot (FP) lasers as potential neuromorphic computing machines with parallel processing capabilities.

Classification General Classification

FenceMask: A Data Augmentation Approach for Pre-extracted Image Features

no code implementations14 Jun 2020 Pu Li, Xiang-Yang Li, Xiang Long

It is based on the 'simulation of object occlusion' strategy, which aim to achieve the balance between object occlusion and information retention of the input data.

Data Augmentation Fine-Grained Visual Categorization +1

Layer Pruning via Fusible Residual Convolutional Block for Deep Neural Networks

no code implementations29 Nov 2020 Pengtao Xu, Jian Cao, Fanhua Shang, Wenyu Sun, Pu Li

For layer pruning, we convert convolutional layers of network into ResConv with a layer scaling factor.

An Once-for-All Budgeted Pruning Framework for ConvNets Considering Input Resolution

no code implementations2 Dec 2020 Wenyu Sun, Jian Cao, Pengtao Xu, Xiangcheng Liu, Pu Li

We propose an efficient once-for-all budgeted pruning framework (OFARPruning) to find many compact network structures close to winner tickets in the early training stage considering the effect of input resolution during the pruning process.

Image Classification object-detection +1

MVP-Net: Multiple View Pointwise Semantic Segmentation of Large-Scale Point Clouds

no code implementations30 Jan 2022 Chuanyu Luo, Xiaohan Li, Nuo Cheng, Han Li, Shengguang Lei, Pu Li

The pipeline of most pointwise point cloud semantic segmentation methods includes points sampling, neighbor searching, feature aggregation, and classification.

Autonomous Driving Segmentation +1

Mini-PointNetPlus: a local feature descriptor in deep learning model for 3d environment perception

no code implementations25 Jul 2023 Chuanyu Luo, Nuo Cheng, Sikun Ma, Jun Xiang, Xiaohan Li, Shengguang Lei, Pu Li

The pioneer work PointNet has been widely applied as a local feature descriptor, a fundamental component in deep learning models for 3D perception, to extract features of a point cloud.

3D Object Visibility Prediction in Autonomous Driving

no code implementations6 Mar 2024 Chuanyu Luo, Nuo Cheng, Ren Zhong, Haipeng Jiang, Wenyu Chen, Aoli Wang, Pu Li

With the rapid advancement of hardware and software technologies, research in autonomous driving has seen significant growth.

Attribute Autonomous Driving +3

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