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.
Ranked #128 on Object Detection on COCO test-dev
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.
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.
4 code implementations • CVPR 2019 • Yihui He, Chenchen Zhu, Jianren Wang, Marios Savvides, Xiangyu Zhang
Large-scale object detection datasets (e. g., MS-COCO) try to define the ground truth bounding boxes as clear as possible.
Ranked #22 on Object Detection on PASCAL VOC 2007
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'.
Ranked #1 on 3D Hand Pose Estimation on InterHand2.6M
1 code implementation • 24 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.
1 code implementation • 6 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.
1 code implementation • 25 May 2017 • Yihui He, Ming Xiang
We evaluate greedy, 2-opt, and genetic algorithms.
1 code implementation • 1 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.
no code implementations • 23 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.
no code implementations • 20 Sep 2017 • Yihui He
We build a RGBD dataset based on RGB dataset and do image classification on it.
no code implementations • 22 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.
no code implementations • 21 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.
no code implementations • 5 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.
no code implementations • 29 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.
no code implementations • 21 Oct 2019 • Yihui He, Jianing Qian, Jianren Wang, Cindy X. Le, Congrui Hetang, Qi Lyu, Wenping Wang, Tianwei Yue
Very deep convolutional neural networks (CNNs) have been firmly established as the primary methods for many computer vision tasks.
no code implementations • 24 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.
no code implementations • 1 Jul 2020 • Jianren Wang, Yihui He
Although our baseline system is a straightforward combination of standard methods, we obtain state-of-the-art results.
no code implementations • 14 Nov 2022 • Yihui He
In this paper, we introduce a new channel pruning method to accelerate very deep convolutional neural networks.
no code implementations • 27 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.
no code implementations • 16 Apr 2024 • Cindy Le, Congrui Hetang, Chendi Lin, Ang Cao, Yihui He
We present EucliDreamer, a simple and effective method to generate textures for 3D models given text prompts and meshes.