Fengwei Yu

Orcid: 0000-0003-0352-8700

According to our database1, Fengwei Yu authored at least 32 papers between 2016 and 2024.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
Towards Frame Rate Agnostic Multi-object Tracking.
Int. J. Comput. Vis., May, 2024

2023
The Equalization Losses: Gradient-Driven Training for Long-tailed Object Recognition.
IEEE Trans. Pattern Anal. Mach. Intell., November, 2023

SysNoise: Exploring and Benchmarking Training-Deployment System Inconsistency.
Proceedings of the Sixth Conference on Machine Learning and Systems, 2023

Exploiting Input Tensor Dynamics in Activation Checkpointing for Efficient Training on GPU.
Proceedings of the IEEE International Parallel and Distributed Processing Symposium, 2023

Exploiting Subgraph Similarities for Efficient Auto-tuning of Tensor Programs.
Proceedings of the 52nd International Conference on Parallel Processing, 2023

UniHCP: A Unified Model for Human-Centric Perceptions.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022
Improving Long-tailed Object Detection with Image-Level Supervision by Multi-Task Collaborative Learning.
CoRR, 2022

The Equalization Losses: Gradient-Driven Training for Long-tailed Object Recognition.
CoRR, 2022

Mimose: An Input-Aware Checkpointing Planner for Efficient Training on GPU.
CoRR, 2022

Equalized Focal Loss for Dense Long-Tailed Object Detection.
CoRR, 2022

Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

NNLQP: A Multi-Platform Neural Network Latency Query and Prediction System with An Evolving Database.
Proceedings of the 51st International Conference on Parallel Processing, 2022

QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantization.
Proceedings of the Tenth International Conference on Learning Representations, 2022

Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm.
Proceedings of the Tenth International Conference on Learning Representations, 2022

Equalized Focal Loss for Dense Long-Tailed Object Detection.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

2021
INTERN: A New Learning Paradigm Towards General Vision.
CoRR, 2021

RobustART: Benchmarking Robustness on Architecture Design and Training Techniques.
CoRR, 2021

MQBench: Towards Reproducible and Deployable Model Quantization Benchmark.
Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1, 2021

Real World Robustness from Systematic Noise.
Proceedings of the ADVM '21: Proceedings of the 1st International Workshop on Adversarial Learning for Multimedia, 2021

BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction.
Proceedings of the 9th International Conference on Learning Representations, 2021

Differentiable Dynamic Wirings for Neural Networks.
Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

Incorporating Convolution Designs into Visual Transformers.
Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

Once Quantization-Aware Training: High Performance Extremely Low-bit Architecture Search.
Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

MixMix: All You Need for Data-Free Compression Are Feature and Data Mixing.
Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

Diversifying Sample Generation for Accurate Data-Free Quantization.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

2020
Learning in School: Multi-teacher Knowledge Inversion for Data-Free Quantization.
CoRR, 2020

Efficient Bitwidth Search for Practical Mixed Precision Neural Network.
CoRR, 2020

Extremely Low-bit Convolution Optimization for Quantized Neural Network on Modern Computer Architectures.
Proceedings of the ICPP 2020: 49th International Conference on Parallel Processing, 2020

Towards Unified INT8 Training for Convolutional Neural Network.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

Forward and Backward Information Retention for Accurate Binary Neural Networks.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

2019
Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networks.
Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019

2016
POI: Multiple Object Tracking with High Performance Detection and Appearance Feature.
Proceedings of the Computer Vision - ECCV 2016 Workshops, 2016


  Loading...