Zhiqiang Shen

32

Papers

219

Total Citations

Papers (32)

Soft Anchor-Point Object Detection

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

Learning Graph Invariance by Harnessing Spuriosity

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

Empowering Graph Invariance Learning with Deep Spurious Infomax

Weakly Supervised Dense Video Captioning

Towards Instance-Level Image-To-Image Translation

Binarizing MobileNet via Evolution-Based Searching

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

Unsupervised Disentanglement of Linear-Encoded Facial Semantics

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

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

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

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

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

Multiple Granularity Descriptors for Fine-Grained Categorization

DSOD: Learning Deeply Supervised Object Detectors From Scratch

Learning Efficient Convolutional Networks Through Network Slimming

Contrast and Order Representations for Video Self-Supervised Learning

FerKD: Surgical Label Adaptation for Efficient Distillation

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

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

ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functions

Online Ensemble Model Compression using Knowledge Distillation

Data-Free Neural Architecture Search via Recursive Label Calibration

A Fast Knowledge Distillation Framework for Visual Recognition

Sliced Recursive Transformer

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

One Last Attention for Your Vision-Language Model

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

ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet Accuracy

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