kaigelee
My current research interests include image semantic segmentation, unsupervised domain adaptation, and adversarial attack.
Beihang University,school of computer science and and EngineeringBei Jing
Pinned Repositories
-
Official Implementation of Harnessing Perceptual Adversarial Patches for Crowd Counting (ACM CCS)
adversarial-attacks
Code for our CVPR 2018 paper, "On the Robustness of Semantic Segmentation Models to Adversarial Attacks"
Adversarial-Attacks-and-Defenses-on-Semantic-Segmentation-Networks
The repo is a source code for the project on Adversarial examples on Semantic Segmentation Networks
CCM
[ECCV2020] Content-Consistent Matching for Domain Adaptive Semantic Segmentation
CSFCN
Real-time Semantic Segmentation
LBAM_Pytorch
Pytorch re-implementation of Paper: Image Inpainting with Learnable Bidirectional Attention Maps (ICCV 2019)
MIC
Official Implementation of MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation
SANet
Real-Time Semantic Segmentation of Street Scenes
TIP
Domain-Adaptive Semantic Segmentation
TransferAttack
TransferAttack is a pytorch framework to boost the adversarial transferability for image classification.
kaigelee's Repositories
kaigelee/CSFCN
Real-time Semantic Segmentation
kaigelee/SANet
Real-Time Semantic Segmentation of Street Scenes
kaigelee/TIP
Domain-Adaptive Semantic Segmentation
kaigelee/CCM
[ECCV2020] Content-Consistent Matching for Domain Adaptive Semantic Segmentation
kaigelee/MIC
Official Implementation of MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation
kaigelee/TransferAttack
TransferAttack is a pytorch framework to boost the adversarial transferability for image classification.
kaigelee/-
Official Implementation of Harnessing Perceptual Adversarial Patches for Crowd Counting (ACM CCS)
kaigelee/gen-efficientnet-pytorch
Pretrained EfficientNet, EfficientNet-Lite, MixNet, MobileNetV3 / V2, MNASNet A1 and B1, FBNet, Single-Path NAS
kaigelee/CLIP-Count
[ACM MM23] CLIP-Count: Towards Text-Guided Zero-Shot Object Counting
kaigelee/clip_dinoiser
Official implementation of 'CLIP-DINOiser: Teaching CLIP a few DINO tricks' paper.
kaigelee/DAFormer
[CVPR22] Official Implementation of DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation
kaigelee/DGInStyle
DGInStyle: Domain-Generalizable Semantic Segmentation with Image Diffusion Models and Stylized Semantic Control
kaigelee/DSRL
Implementation of CVPR 2020 Dual Super-Resolution Learning for Semantic Segmentation
kaigelee/EBAD
Code repository for Ensemble-based Blackbox Attacks on Dense Prediction (EBAD), CVPR 2023
kaigelee/finetune-anything
Fine-tuning SAMs for class-aware computer vision tasks in specific scenarios
kaigelee/GiT
Official Implementation of "GiT: Towards Generalist Vision Transformer through Universal Language Interface"
kaigelee/ImageNet_val-for-ImageFolder
an ImageNet (ILSVRC2012) validation dataset for torchvision.datasets.ImageFolder
kaigelee/kaigelee.github.io
kaigelee/lama
🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022
kaigelee/MAP
Boosting Adversarial Transferability of Black-Box Attack
kaigelee/PatchAttackTool
Repository for patch attacks against autonomous driving vision tasks.
kaigelee/Rank1-Ali-Tianchi-Real-World-Image-Forgery-Localization-Challenge
2022阿里天池真实场景篡改图像检测挑战赛-冠军方案(1/1149)
kaigelee/Segmentation-Pytorch
Semantic Segmentation in Pytorch. Network include: FCN、FCN_ResNet、SegNet、UNet、BiSeNet、BiSeNetV2、PSPNet、DeepLabv3_plus、 HRNet、DDRNet
kaigelee/segmentation_pytorch
Simple image segmentation pipeline in pytorch, using HRNet and SegFormer models
kaigelee/semantic-segmentation
SOTA Semantic Segmentation Models in PyTorch
kaigelee/SemSegAdvPatch
kaigelee/SFOCDA
Source-Free Open Compound Domain Adaptation in Semantic Segmentation. IEEE TCSVT
kaigelee/SSA
Spectrum simulation attack (ECCV'2022 Oral) towards boosting the transferability of adversarial examples
kaigelee/UHDM
(ECCV2022) This is the official PyTorch implementation of ECCV2022 paper: Towards Efficient and Scale-Robust Ultra-High-Definition Image Demoireing
kaigelee/VT
Enhancing the Transferability of Adversarial Attacks through Variance Tuning