Kai Han

Orcid: 0000-0002-9761-2702

Affiliations:
  • Huawei Technologies, Noah's Ark Lab
  • Peking University, MOE Key Laboratory of Machine Perception / Cooperative Medianet Innovation Center, Beijing, China (former)


According to our database1, Kai Han authored at least 88 papers between 2017 and 2024.

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

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
Local Means Binary Networks for Image Super-Resolution.
IEEE Trans. Neural Networks Learn. Syst., May, 2024

GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer.
CoRR, 2024

EMS-SD: Efficient Multi-sample Speculative Decoding for Accelerating Large Language Models.
CoRR, 2024

Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning.
CoRR, 2024

Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting.
CoRR, 2024

GhostNetV3: Exploring the Training Strategies for Compact Models.
CoRR, 2024

A robust audio deepfake detection system via multi-view feature.
CoRR, 2024

DenseMamba: State Space Models with Dense Hidden Connection for Efficient Large Language Models.
CoRR, 2024

SAM-DiffSR: Structure-Modulated Diffusion Model for Image Super-Resolution.
CoRR, 2024

A Survey on Transformer Compression.
CoRR, 2024

Data-efficient Large Vision Models through Sequential Autoregression.
CoRR, 2024

Vision Superalignment: Weak-to-Strong Generalization for Vision Foundation Models.
CoRR, 2024

Rethinking Optimization and Architecture for Tiny Language Models.
CoRR, 2024

An Empirical Study of Scaling Law for OCR.
CoRR, 2024

2023
A Survey on Vision Transformer.
IEEE Trans. Pattern Anal. Mach. Intell., 2023

PanGu-π: Enhancing Language Model Architectures via Nonlinearity Compensation.
CoRR, 2023

LightCLIP: Learning Multi-Level Interaction for Lightweight Vision-Language Models.
CoRR, 2023

One-for-All: Bridge the Gap Between Heterogeneous Architectures in Knowledge Distillation.
CoRR, 2023

Category Feature Transformer for Semantic Segmentation.
CoRR, 2023

ParameterNet: Parameters Are All You Need for Large-scale Visual Pretraining of Mobile Networks.
CoRR, 2023

GPT4Image: Can Large Pre-trained Models Help Vision Models on Perception Tasks?
CoRR, 2023

VanillaKD: Revisit the Power of Vanilla Knowledge Distillation from Small Scale to Large Scale.
CoRR, 2023

Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanism.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Species196: A One-Million Semi-supervised Dataset for Fine-grained Species Recognition.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

One-for-All: Bridge the Gap Between Heterogeneous Architectures in Knowledge Distillation.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Revisit the Power of Vanilla Knowledge Distillation: from Small Scale to Large Scale.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

GhostRNN: Reducing State Redundancy in RNN with Cheap Operations.
Proceedings of the 24th Annual Conference of the International Speech Communication Association, 2023

Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Boosting Semantic Segmentation from the Perspective of Explicit Class Embeddings.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Masked Image Modeling with Local Multi-Scale Reconstruction.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

Network Expansion For Practical Training Acceleration.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022
GhostSR: Learning Ghost Features for Efficient Image Super-Resolution.
Trans. Mach. Learn. Res., 2022

Learning Versatile Convolution Filters for Efficient Visual Recognition.
IEEE Trans. Pattern Anal. Mach. Intell., 2022

GhostNets on Heterogeneous Devices via Cheap Operations.
Int. J. Comput. Vis., 2022

FastMIM: Expediting Masked Image Modeling Pre-training for Vision.
CoRR, 2022

PyramidTNT: Improved Transformer-in-Transformer Baselines with Pyramid Architecture.
CoRR, 2022

GhostNetV2: Enhance Cheap Operation with Long-Range Attention.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Accelerating Sparse Convolution with Column Vector-Wise Sparsity.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Redistribution of Weights and Activations for AdderNet Quantization.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

A Transformer-Based Object Detector with Coarse-Fine Crossing Representations.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Learning Efficient Vision Transformers via Fine-Grained Manifold Distillation.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Vision GNN: An Image is Worth Graph of Nodes.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

An Image Patch is a Wave: Phase-Aware Vision MLP.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

Patch Slimming for Efficient Vision Transformers.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

Network Amplification with Efficient MACs Allocation.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022

Hire-MLP: Vision MLP via Hierarchical Rearrangement.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

CMT: Convolutional Neural Networks Meet Vision Transformers.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

Instance-Aware Dynamic Neural Network Quantization.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

2021
Greedy Network Enlarging.
CoRR, 2021

CMT: Convolutional Neural Networks Meet Vision Transformers.
CoRR, 2021

Efficient Vision Transformers via Fine-Grained Manifold Distillation.
CoRR, 2021

Post-Training Quantization for Vision Transformer.
CoRR, 2021

Visual Transformer Pruning.
CoRR, 2021

AdderNet and its Minimalist Hardware Design for Energy-Efficient Artificial Intelligence.
CoRR, 2021

GhostSR: Learning Ghost Features for Efficient Image Super-Resolution.
CoRR, 2021

Mining Neighbor Frames for Person Re-identification by Global Optimal Tracking.
Proceedings of the Advances in Swarm Intelligence - 12th International Conference, 2021

Dynamic Resolution Network.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Learning Frequency Domain Approximation for Binary Neural Networks.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Augmented Shortcuts for Vision Transformers.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Post-Training Quantization for Vision Transformer.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Transformer in Transformer.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

ReNAS: Relativistic Evaluation of Neural Architecture Search.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

Positive-Unlabeled Data Purification in the Wild for Object Detection.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

Distilling Object Detectors via Decoupled Features.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

Multi-bit Adaptive Distillation for Binary Neural Networks.
Proceedings of the 32nd British Machine Vision Conference 2021, 2021

2020
A Survey on Visual Transformer.
CoRR, 2020

Dynamic Feature Pyramid Networks for Object Detection.
CoRR, 2020

VEGA: Towards an End-to-End Configurable AutoML Pipeline.
CoRR, 2020

Widening and Squeezing: Towards Accurate and Efficient QNNs.
CoRR, 2020

Searching for Low-Bit Weights in Quantized Neural Networks.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Model Rubik's Cube: Twisting Resolution, Depth and Width for TinyNets.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Training Binary Neural Networks through Learning with Noisy Supervision.
Proceedings of the 37th International Conference on Machine Learning, 2020

GhostNet: More Features From Cheap Operations.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

Hit-Detector: Hierarchical Trinity Architecture Search for Object Detection.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

2019
RNAS: Architecture Ranking for Powerful Networks.
CoRR, 2019

Balanced Binary Neural Networks with Gated Residual.
CoRR, 2019

Full-Stack Filters to Build Minimum Viable CNNs.
CoRR, 2019

Positive-Unlabeled Compression on the Cloud.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Learning Instance-wise Sparsity for Accelerating Deep Models.
Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, 2019

Attribute Aware Pooling for Pedestrian Attribute Recognition.
Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, 2019

Searching for Accurate Binary Neural Architectures.
Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision Workshops, 2019

Co-Evolutionary Compression for Unpaired Image Translation.
Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019

Beyond Human Parts: Dual Part-Aligned Representations for Person Re-Identification.
Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019

Low-resolution Visual Recognition via Deep Feature Distillation.
Proceedings of the IEEE International Conference on Acoustics, 2019

2018
Greedy Hash: Towards Fast Optimization for Accurate Hash Coding in CNN.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Attribute-Aware Attention Model for Fine-grained Representation Learning.
Proceedings of the 2018 ACM Multimedia Conference on Multimedia Conference, 2018

Autoencoder Inspired Unsupervised Feature Selection.
Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

2017
Autoencoder Feature Selector.
CoRR, 2017


  Loading...