Search Results for author: Yihui He

Found 20 papers, 9 papers with code

Single Image Super-resolution via a Lightweight Residual Convolutional Neural Network

no code implementations23 Mar 2017 Yudong Liang, Ze Yang, Kai Zhang, Yihui He, Jinjun Wang, Nanning Zheng

To tackle with the second problem, a lightweight CNN architecture which has carefully designed width, depth and skip connections was proposed.

Image Super-Resolution SSIM

Vehicle Traffic Driven Camera Placement for Better Metropolis Security Surveillance

1 code implementation1 Apr 2017 Yihui He, Xiaobo Ma, Xiapu Luo, Jianfeng Li, Mengchen Zhao, Bo An, Xiaohong Guan

Security surveillance is one of the most important issues in smart cities, especially in an era of terrorism.

Decision Making

Channel Pruning for Accelerating Very Deep Neural Networks

1 code implementation ICCV 2017 Yihui He, Xiangyu Zhang, Jian Sun

In this paper, we introduce a new channel pruning method to accelerate very deep convolutional neural networks. Given a trained CNN model, we propose an iterative two-step algorithm to effectively prune each layer, by a LASSO regression based channel selection and least square reconstruction.

regression

Estimated Depth Map Helps Image Classification

no code implementations20 Sep 2017 Yihui He

We build a RGBD dataset based on RGB dataset and do image classification on it.

Classification Depth Estimation +3

AMC: AutoML for Model Compression and Acceleration on Mobile Devices

12 code implementations ECCV 2018 Yihui He, Ji Lin, Zhijian Liu, Hanrui Wang, Li-Jia Li, Song Han

Model compression is a critical technique to efficiently deploy neural network models on mobile devices which have limited computation resources and tight power budgets.

Model Compression Neural Architecture Search

Shift-based Primitives for Efficient Convolutional Neural Networks

no code implementations22 Sep 2018 Huasong Zhong, Xianggen Liu, Yihui He, Yuchun Ma

These three primitives (channel shift, address shift, shortcut shift) can reduce the inference time on GPU while maintains the prediction accuracy.

An Empirical Analysis of Deep Audio-Visual Models for Speech Recognition

no code implementations21 Dec 2018 Devesh Walawalkar, Yihui He, Rohit Pillai

In this project, we worked on speech recognition, specifically predicting individual words based on both the video frames and audio.

Lip Reading speech-recognition +1

Feature Selective Anchor-Free Module for Single-Shot Object Detection

4 code implementations CVPR 2019 Chenchen Zhu, Yihui He, Marios Savvides

The general concept of the FSAF module is online feature selection applied to the training of multi-level anchor-free branches.

feature selection object-detection +1

Prediction-Tracking-Segmentation

no code implementations5 Apr 2019 Jianren Wang, Yihui He, Xiaobo Wang, Xinjia Yu, Xia Chen

We introduce a prediction driven method for visual tracking and segmentation in videos.

Segmentation Video Segmentation +2

MoBiNet: A Mobile Binary Network for Image Classification

no code implementations29 Jul 2019 Hai Phan, Dang Huynh, Yihui He, Marios Savvides, Zhiqiang Shen

MobileNet and Binary Neural Networks are two among the most widely used techniques to construct deep learning models for performing a variety of tasks on mobile and embedded platforms. In this paper, we present a simple yet efficient scheme to exploit MobileNet binarization at activation function and model weights.

Binarization Classification +2

Deep Mixture Density Network for Probabilistic Object Detection

no code implementations24 Nov 2019 Yihui He, Jianren Wang

The covariances help to learn the relationship between the borders, and the mixture components potentially learn different configurations of an occluded part.

Object object-detection +2

Epipolar Transformers

1 code implementation CVPR 2020 Yihui He, Rui Yan, Katerina Fragkiadaki, Shoou-I Yu

The intuition is: given a 2D location p in the current view, we would like to first find its corresponding point p' in a neighboring view, and then combine the features at p' with the features at p, thus leading to a 3D-aware feature at p. Inspired by stereo matching, the epipolar transformer leverages epipolar constraints and feature matching to approximate the features at p'.

2D Pose Estimation 3D Hand Pose Estimation +3

Motion Prediction in Visual Object Tracking

no code implementations1 Jul 2020 Jianren Wang, Yihui He

Although our baseline system is a straightforward combination of standard methods, we obtain state-of-the-art results.

Autonomous Driving motion prediction +5

Pruning Very Deep Neural Network Channels for Efficient Inference

no code implementations14 Nov 2022 Yihui He

In this paper, we introduce a new channel pruning method to accelerate very deep convolutional neural networks.

Fast and Interpretable Face Identification for Out-Of-Distribution Data Using Vision Transformers

1 code implementation6 Nov 2023 Hai Phan, Cindy Le, Vu Le, Yihui He, Anh Totti Nguyen

DeepFace-EMD (Phan et al. 2022) reaches state-of-the-art accuracy on out-of-distribution data by first comparing two images at the image level, and then at the patch level.

Face Identification Re-Ranking

EucliDreamer: Fast and High-Quality Texturing for 3D Models with Stable Diffusion Depth

no code implementations27 Nov 2023 Cindy Le, Congrui Hetang, Chendi Lin, Ang Cao, Yihui He

This paper presents a novel method to generate textures for 3D models given text prompts and 3D meshes.

Data Augmentation

Segment Anything Model for Road Network Graph Extraction

1 code implementation24 Mar 2024 Congrui Hetang, Haoru Xue, Cindy Le, Tianwei Yue, Wenping Wang, Yihui He

We propose SAM-Road, an adaptation of the Segment Anything Model (SAM) for extracting large-scale, vectorized road network graphs from satellite imagery.

Graph Learning Semantic Segmentation

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