Jianxin Wu

papers

1,306

total citations

papers (22)

Jianxin Wu

papers (22)

ActionFormer: Localizing Moments of Actions with Transformers

Residual Attention: A Simple but Effective Method for Multi-Label Recognition

Neural Network Pruning With Residual-Connections and Limited-Data

Distilling Virtual Examples for Long-Tailed Recognition

Rethinking the Route Towards Weakly Supervised Object Localization

Webly Supervised Fine-Grained Recognition: Benchmark Datasets and an Approach

Training Vision Transformers with Only 2040 Images

DTL: Disentangled Transfer Learning for Visual Recognition

Multi-Label Self-Supervised Learning with Scene Images

No One Left Behind: Improving the Worst Categories in Long-Tailed Learning

Salvage of Supervision in Weakly Supervised Object Detection

Quantization without Tears

Compressing Models With Few Samples: Mimicking Then Replacing

Practical Network Acceleration With Tiny Sets

Synergistic Self-Supervised and Quantization Learning

Worst Case Matters for Few-Shot Recognition

All You Need in Knowledge Distillation Is a Tailored Coordinate System

GPLQ: A General, Practical, and Lightning QAT Method for Vision Transformers

Rectify the Regression Bias in Long-Tailed Object Detection

Treasures in Discarded Weights for LLM Quantization

Minimal Interaction Seperated Tuning: A New Paradigm for Visual Adaptation

Memory-Efficient Generative Models via Product Quantization

papers (22)

ActionFormer: Localizing Moments of Actions with Transformers

Residual Attention: A Simple but Effective Method for Multi-Label Recognition

Neural Network Pruning With Residual-Connections and Limited-Data

Distilling Virtual Examples for Long-Tailed Recognition

Rethinking the Route Towards Weakly Supervised Object Localization

Webly Supervised Fine-Grained Recognition: Benchmark Datasets and an Approach

Training Vision Transformers with Only 2040 Images

DTL: Disentangled Transfer Learning for Visual Recognition

Multi-Label Self-Supervised Learning with Scene Images

No One Left Behind: Improving the Worst Categories in Long-Tailed Learning

Salvage of Supervision in Weakly Supervised Object Detection

Quantization without Tears

Compressing Models With Few Samples: Mimicking Then Replacing

Practical Network Acceleration With Tiny Sets

Synergistic Self-Supervised and Quantization Learning

Worst Case Matters for Few-Shot Recognition

All You Need in Knowledge Distillation Is a Tailored Coordinate System

GPLQ: A General, Practical, and Lightning QAT Method for Vision Transformers

Rectify the Regression Bias in Long-Tailed Object Detection

Treasures in Discarded Weights for LLM Quantization

Minimal Interaction Seperated Tuning: A New Paradigm for Visual Adaptation

Memory-Efficient Generative Models via Product Quantization