KaigeLi's Projects
Official Implementation of Harnessing Perceptual Adversarial Patches for Crowd Counting (ACM CCS)
Code for our CVPR 2018 paper, "On the Robustness of Semantic Segmentation Models to Adversarial Attacks"
The repo is a source code for the project on Adversarial examples on Semantic Segmentation Networks
A collection of AWESOME things about domian adaptation
[ECCV2020] Content-Consistent Matching for Domain Adaptive Semantic Segmentation
[ACM MM23] CLIP-Count: Towards Text-Guided Zero-Shot Object Counting
Official implementation of 'CLIP-DINOiser: Teaching CLIP a few DINO tricks' paper.
Real-time Semantic Segmentation
[CVPR22] Official Implementation of DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation
DGInStyle: Domain-Generalizable Semantic Segmentation with Image Diffusion Models and Stylized Semantic Control
Pytorch Implementation -- All about Structure: Adapting Structural Information across Domains for Boosting Semantic Segmentation, CVPR 2019
Implementation of CVPR 2020 Dual Super-Resolution Learning for Semantic Segmentation
Code repository for Ensemble-based Blackbox Attacks on Dense Prediction (EBAD), CVPR 2023
Fine-tuning SAMs for class-aware computer vision tasks in specific scenarios
Pretrained EfficientNet, EfficientNet-Lite, MixNet, MobileNetV3 / V2, MNASNet A1 and B1, FBNet, Single-Path NAS
Official Implementation of "GiT: Towards Generalist Vision Transformer through Universal Language Interface"
an ImageNet (ILSVRC2012) validation dataset for torchvision.datasets.ImageFolder
🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022
Pytorch re-implementation of Paper: Image Inpainting with Learnable Bidirectional Attention Maps (ICCV 2019)
Learning from Synthetic Data: Addressing Domain Shift for Semantic Segmentation
Boosting Adversarial Transferability of Black-Box Attack
Official Implementation of MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation
mmdetection源码注释
Repository for patch attacks against autonomous driving vision tasks.
Pytorch implementation with segmentation model and adversarial attacks
2022阿里天池真实场景篡改图像检测挑战赛-冠军方案(1/1149)
PyTorch training code for FastSeg: https://github.com/ekzhang/fastseg
Relative Total Variation(a method for structure extraction from texture)
Real-Time Semantic Segmentation of Street Scenes