Search Results for author: Feiyu Zhu

Found 11 papers, 5 papers with code

Sample-Efficient Behavior Cloning Using General Domain Knowledge

no code implementations27 Jan 2025 Feiyu Zhu, Jean Oh, Reid Simmons

Behavior cloning has shown success in many sequential decision-making tasks by learning from expert demonstrations, yet they can be very sample inefficient and fail to generalize to unseen scenarios.

Car Racing Feature Engineering +2

Faster Multi-GPU Training with PPLL: A Pipeline Parallelism Framework Leveraging Local Learning

no code implementations19 Nov 2024 Xiuyuan Guo, Chengqi Xu, Guinan Guo, Feiyu Zhu, Changpeng Cai, Peizhe Wang, Xiaoming Wei, Junhao Su, Jialin Gao

To address this issue, we present PPLL (Pipeline Parallelism based on Local Learning), a novel framework that leverages local learning algorithms to enable effective parallel training across multiple GPUs.

LAKD-Activation Mapping Distillation Based on Local Learning

no code implementations21 Aug 2024 Yaoze Zhang, Yuming Zhang, Yu Zhao, Yue Zhang, Feiyu Zhu

Existing knowledge distillation methods focus on designing different distillation targets to acquire knowledge from teacher models.

Knowledge Distillation

HPFF: Hierarchical Locally Supervised Learning with Patch Feature Fusion

1 code implementation8 Jul 2024 Junhao Su, Chenghao He, Feiyu Zhu, Xiaojie Xu, Dongzhi Guan, Chenyang Si

To overcome these limitations, we propose a novel model called HPFF that performs hierarchical locally supervised learning and patch-level feature computation on the auxiliary networks.

Momentum Auxiliary Network for Supervised Local Learning

1 code implementation8 Jul 2024 Junhao Su, Changpeng Cai, Feiyu Zhu, Chenghao He, Xiaojie Xu, Dongzhi Guan, Chenyang Si

Supervised local learning, which segments the network into multiple local blocks updated by independent auxiliary networks.

Image Classification

Advancing Supervised Local Learning Beyond Classification with Long-term Feature Bank

no code implementations1 Jun 2024 Feiyu Zhu, Yuming Zhang, Changpeng Cai, Chenghao He, Xiuyuan Guo, Jiao Li, Peizhe Wang, Junhao Su, Jialin Gao

Local learning offers an alternative to traditional end-to-end back-propagation in deep neural networks, significantly reducing GPU memory usage.

Image Classification object-detection +2

SSPNet: Scale Selection Pyramid Network for Tiny Person Detection from UAV Images

2 code implementations4 Jul 2021 Mingbo Hong, Shuiwang Li, Yuchao Yang, Feiyu Zhu, Qijun Zhao, Li Lu

With the increasing demand for search and rescue, it is highly demanded to detect objects of interest in large-scale images captured by Unmanned Aerial Vehicles (UAVs), which is quite challenging due to extremely small scales of objects.

Human Detection

Watermark Faker: Towards Forgery of Digital Image Watermarking

1 code implementation23 Mar 2021 Ruowei Wang, Chenguo Lin, Qijun Zhao, Feiyu Zhu

Digital watermarking has been widely used to protect the copyright and integrity of multimedia data.

Image Generation

SQE: a Self Quality Evaluation Metric for Parameters Optimization in Multi-Object Tracking

no code implementations CVPR 2020 Yanru Huang, Feiyu Zhu, Zheni Zeng, Xi Qiu, Yuan Shen, Jia-Nan Wu

We present a novel self quality evaluation metric SQE for parameters optimization in the challenging yet critical multi-object tracking task.

Multi-Object Tracking

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