Zhiqiang Shen

papers

1,644

total citations

papers (27)

ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functions

ECCV 2020arXiv

404

citations

Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detection

CVPR 2021arXiv

205

citations

Soft Anchor-Point Object Detection

ECCV 2020arXiv

159

citations

Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation

CVPR 2022arXiv

146

citations

Squeeze, Recover and Relabel: Dataset Condensation at ImageNet Scale From A New Perspective

NEURIPS 2023arXiv

125

citations

PromptCAL: Contrastive Affinity Learning via Auxiliary Prompts for Generalized Novel Category Discovery

CVPR 2023arXiv

106

citations

Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space

CVPR 2022arXiv

citations

A Fast Knowledge Distillation Framework for Visual Recognition

ECCV 2022arXiv

citations

Generalized Large-Scale Data Condensation via Various Backbone and Statistical Matching

CVPR 2024arXiv

citations

S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-Bit Neural Networks via Guided Distribution Calibration

CVPR 2021arXiv

citations

PointCMP: Contrastive Mask Prediction for Self-Supervised Learning on Point Cloud Videos

CVPR 2023arXiv

citations

Masked Spatio-Temporal Structure Prediction for Self-supervised Learning on Point Cloud Videos

ICCV 2023arXiv

citations

Empowering Graph Invariance Learning with Deep Spurious Infomax

ICML 2024arXiv

citations

Point Contrastive Prediction with Semantic Clustering for Self-Supervised Learning on Point Cloud Videos

ICCV 2023arXiv

citations

Unsupervised Disentanglement of Linear-Encoded Facial Semantics

CVPR 2021arXiv

citations

DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation

CVPR 2025arXiv

citations

Data-Free Neural Architecture Search via Recursive Label Calibration

ECCV 2022arXiv

citations

Learning Graph Invariance by Harnessing Spuriosity

ICLR 2025

citations

FerKD: Surgical Label Adaptation for Efficient Distillation

ICCV 2023arXiv

citations

MosaicDiff: Training-free Structural Pruning for Diffusion Model Acceleration Reflecting Pretraining Dynamics

ICCV 2025arXiv

citations

One Last Attention for Your Vision-Language Model

ICCV 2025arXiv

citations

Contrast and Order Representations for Video Self-Supervised Learning

ICCV 2021

citations

S3A: Towards Realistic Zero-Shot Classification via Self Structural Semantic Alignment

AAAI 2024

citations

Zhiqiang Shen

papers (27)

ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functions

Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detection

Soft Anchor-Point Object Detection

Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation

Squeeze, Recover and Relabel: Dataset Condensation at ImageNet Scale From A New Perspective

PromptCAL: Contrastive Affinity Learning via Auxiliary Prompts for Generalized Novel Category Discovery

Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space

A Fast Knowledge Distillation Framework for Visual Recognition

Generalized Large-Scale Data Condensation via Various Backbone and Statistical Matching

Online Ensemble Model Compression using Knowledge Distillation

Binarizing MobileNet via Evolution-Based Searching

Sliced Recursive Transformer

ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet Accuracy

S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-Bit Neural Networks via Guided Distribution Calibration

PointCMP: Contrastive Mask Prediction for Self-Supervised Learning on Point Cloud Videos

Masked Spatio-Temporal Structure Prediction for Self-supervised Learning on Point Cloud Videos

Empowering Graph Invariance Learning with Deep Spurious Infomax

Point Contrastive Prediction with Semantic Clustering for Self-Supervised Learning on Point Cloud Videos

Unsupervised Disentanglement of Linear-Encoded Facial Semantics

DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation

Data-Free Neural Architecture Search via Recursive Label Calibration

Learning Graph Invariance by Harnessing Spuriosity

FerKD: Surgical Label Adaptation for Efficient Distillation

MosaicDiff: Training-free Structural Pruning for Diffusion Model Acceleration Reflecting Pretraining Dynamics

One Last Attention for Your Vision-Language Model

Contrast and Order Representations for Video Self-Supervised Learning

S3A: Towards Realistic Zero-Shot Classification via Self Structural Semantic Alignment

papers (27)

ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functions

Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detection

Soft Anchor-Point Object Detection

Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation

Squeeze, Recover and Relabel: Dataset Condensation at ImageNet Scale From A New Perspective

PromptCAL: Contrastive Affinity Learning via Auxiliary Prompts for Generalized Novel Category Discovery

Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space

A Fast Knowledge Distillation Framework for Visual Recognition

Generalized Large-Scale Data Condensation via Various Backbone and Statistical Matching

Online Ensemble Model Compression using Knowledge Distillation

Binarizing MobileNet via Evolution-Based Searching

Sliced Recursive Transformer

ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet Accuracy

S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-Bit Neural Networks via Guided Distribution Calibration

PointCMP: Contrastive Mask Prediction for Self-Supervised Learning on Point Cloud Videos

Masked Spatio-Temporal Structure Prediction for Self-supervised Learning on Point Cloud Videos

Empowering Graph Invariance Learning with Deep Spurious Infomax

Point Contrastive Prediction with Semantic Clustering for Self-Supervised Learning on Point Cloud Videos

Unsupervised Disentanglement of Linear-Encoded Facial Semantics

DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation

Data-Free Neural Architecture Search via Recursive Label Calibration

Learning Graph Invariance by Harnessing Spuriosity

FerKD: Surgical Label Adaptation for Efficient Distillation

MosaicDiff: Training-free Structural Pruning for Diffusion Model Acceleration Reflecting Pretraining Dynamics

One Last Attention for Your Vision-Language Model

Contrast and Order Representations for Video Self-Supervised Learning

S3A: Towards Realistic Zero-Shot Classification via Self Structural Semantic Alignment