xinyuliu-jeffrey

Decoupled-Unbiased-Teacher

GFBS

[ACM MM'21] Exploring Gradient Flow Based Saliency for DNN Model Compression

NLTE

[CVPR' 22] Towards Robust Adaptive Object Detection under Noisy Annotations

SFPolypDA

[TMI'22] A Source-free Domain Adaptive Polyp Detection Framework with Style Diversification Flow

Cream

This is a collection of our NAS and Vision Transformer work.

adet

AdelaiDet is an open source toolbox for multiple instance-level detection applications.

ConsolidatedPolypDA

[MedIA'21] Consolidated domain adaptive detection and localization framework for cross-device colonoscopic images

Cream

This is a collection of our NAS and Vision Transformer work.

deep-learning-colonoscopy

Review in Deep Learning for Polyp Detection and Classification in Colonoscopy.

EfficientViT_Model_Zoo

This is the model zoo for our CVPR 2023 paper: EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention

xinyuliu-jeffrey/ConsolidatedPolypDA

[MedIA'21] Consolidated domain adaptive detection and localization framework for cross-device colonoscopic images

xinyuliu-jeffrey/EfficientViT_Model_Zoo

This is the model zoo for our CVPR 2023 paper: EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention

xinyuliu-jeffrey/adet

AdelaiDet is an open source toolbox for multiple instance-level detection applications.

xinyuliu-jeffrey/Cream

This is a collection of our NAS and Vision Transformer work.

xinyuliu-jeffrey/deep-learning-colonoscopy

Review in Deep Learning for Polyp Detection and Classification in Colonoscopy.

xinyuliu-jeffrey/EveryPixelMatters

Implementation of ECCV 2020 paper "Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detector"

xinyuliu-jeffrey/FCOS

FCOS: Fully Convolutional One-Stage Object Detection (ICCV'19)

xinyuliu-jeffrey/GFBS

[ACM MM'21] Exploring Gradient Flow Based Saliency for DNN Model Compression

xinyuliu-jeffrey/Swin-Transformer

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

xinyuliu-jeffrey/LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

xinyuliu-jeffrey/Swin-Transformer-Object-Detection

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Object Detection and Instance Segmentation.

xinyuliu-jeffrey/VMamba

VMamba: Visual State Space Models，code is based on mamba

xinyuliu-jeffrey/xinyuliu-jeffrey

Config files for my GitHub profile.