Search Results for author: yanfu Zhang

Found 17 papers, 5 papers with code

Adversarial Nonnegative Matrix Factorization

no code implementations ICML 2020 lei luo, yanfu Zhang, Heng Huang

Nonnegative Matrix Factorization (NMF) has become an increasingly important research topic in machine learning.

Bilevel Optimization

IMUVIE: Pickup Timeline Action Localization via Motion Movies

no code implementations19 Nov 2024 John Clapham, Kenneth Koltermann, yanfu Zhang, Yuming Sun, Evie N Burnet, Gang Zhou

Falls among seniors due to difficulties with tasks such as picking up objects pose significant health and safety risks, impacting quality of life and independence.

Action Classification Action Localization +1

Unlocking Memorization in Large Language Models with Dynamic Soft Prompting

no code implementations20 Sep 2024 Zhepeng Wang, Runxue Bao, Yawen Wu, Jackson Taylor, Cao Xiao, Feng Zheng, Weiwen Jiang, Shangqian Gao, yanfu Zhang

Pretrained large language models (LLMs) have revolutionized natural language processing (NLP) tasks such as summarization, question answering, and translation.

Code Generation Memorization +2

FCDM: Sparse-view Sinogram Inpainting with Frequency Domain Convolution Enhanced Diffusion Models

no code implementations26 Aug 2024 Jiaze E, Srutarshi Banerjee, Tekin Bicer, Guannan Wang, yanfu Zhang, Bin Ren

Computed tomography (CT) is an imaging technique that uses X-ray projections from multiple rotation angles to create detailed cross-sectional images, widely used in industrial inspection and medical diagnostics.

Computed Tomography (CT) CT Reconstruction +1

UniAV: Unified Audio-Visual Perception for Multi-Task Video Event Localization

1 code implementation4 Apr 2024 Tiantian Geng, Teng Wang, yanfu Zhang, Jinming Duan, Weili Guan, Feng Zheng, Ling Shao

Video localization tasks aim to temporally locate specific instances in videos, including temporal action localization (TAL), sound event detection (SED) and audio-visual event localization (AVEL).

audio-visual event localization Event Detection +2

Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratch

1 code implementation CVPR 2024 Xidong Wu, Shangqian Gao, Zeyu Zhang, Zhenzhen Li, Runxue Bao, yanfu Zhang, Xiaoqian Wang, Heng Huang

Current techniques for deep neural network (DNN) pruning often involve intricate multi-step processes that require domain-specific expertise, making their widespread adoption challenging.

Network Pruning

BilevelPruning: Unified Dynamic and Static Channel Pruning for Convolutional Neural Networks

no code implementations CVPR 2024 Shangqian Gao, yanfu Zhang, Feihu Huang, Heng Huang

Most existing dynamic or runtime channel pruning methods have to store all weights to achieve efficient inference which brings extra storage costs.

Device-Wise Federated Network Pruning

no code implementations CVPR 2024 Shangqian Gao, Junyi Li, Zeyu Zhang, yanfu Zhang, Weidong Cai, Heng Huang

Neural network pruning particularly channel pruning is a widely used technique for compressing deep learning models to enable their deployment on edge devices with limited resources.

Edge-computing Federated Learning +1

Structural Alignment for Network Pruning through Partial Regularization

no code implementations ICCV 2023 Shangqian Gao, Zeyu Zhang, yanfu Zhang, Feihu Huang, Heng Huang

To mitigate this gap, we first learn a target sub-network during the model training process, and then we use this sub-network to guide the learning of model weights through partial regularization.

Network Pruning

A Faster Decentralized Algorithm for Nonconvex Minimax Problems

no code implementations NeurIPS 2021 Wenhan Xian, Feihu Huang, yanfu Zhang, Heng Huang

We prove that our DM-HSGD algorithm achieves stochastic first-order oracle (SFO) complexity of $O(\kappa^3 \epsilon^{-3})$ for decentralized stochastic nonconvex-strongly-concave problem to search an $\epsilon$-stationary point, which improves the exiting best theoretical results.

Optimizing Large-Scale Hyperparameters via Automated Learning Algorithm

1 code implementation17 Feb 2021 Bin Gu, Guodong Liu, yanfu Zhang, Xiang Geng, Heng Huang

Modern machine learning algorithms usually involve tuning multiple (from one to thousands) hyperparameters which play a pivotal role in terms of model generalizability.

Hyperparameter Optimization

Exploration and Estimation for Model Compression

no code implementations ICCV 2021 yanfu Zhang, Shangqian Gao, Heng Huang

In this paper, we focus on the discrimination-aware compression of Convolutional Neural Networks (CNNs).

Model Compression

Learning Better Visual Data Similarities via New Grouplet Non-Euclidean Embedding

no code implementations ICCV 2021 yanfu Zhang, Lei Luo, Wenhan Xian, Heng Huang

However, pair-wise methods involve expensive training costs, while proxy-based methods are less accurate in characterizing the relationships between data points.

Metric Learning

Improved Generalization of Heading Direction Estimation for Aerial Filming Using Semi-supervised Regression

no code implementations26 Mar 2019 Wenshan Wang, Aayush Ahuja, Yanfu Zhang, Rogerio Bonatti, Sebastian Scherer

We show that by leveraging unlabeled sequences, the amount of labeled data required can be significantly reduced.

regression

Integrating kinematics and environment context into deep inverse reinforcement learning for predicting off-road vehicle trajectories

1 code implementation16 Oct 2018 Yanfu Zhang, Wenshan Wang, Rogerio Bonatti, Daniel Maturana, Sebastian Scherer

The first-stage network learns feature representations of the environment using low-level LiDAR statistics and the second-stage network combines those learned features with kinematics data.

Autonomous Navigation motion prediction +2

Autonomous drone cinematographer: Using artistic principles to create smooth, safe, occlusion-free trajectories for aerial filming

no code implementations28 Aug 2018 Rogerio Bonatti, yanfu Zhang, Sanjiban Choudhury, Wenshan Wang, Sebastian Scherer

Autonomous aerial cinematography has the potential to enable automatic capture of aesthetically pleasing videos without requiring human intervention, empowering individuals with the capability of high-end film studios.

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