cbsong's repositories
FIN
This is the source code of paper FIN: Flow-based Robust Watermarking with Invertible Noise Layer for Black-box Distortions, which is received by AAAI' 23.
YOLOv8-Openvino
A repository that helps to convert the YOLOv8 detection model to OpenVINO format via onnx and make it more optimized with int8 quantization.
PIMoG-An-Effective-Screen-shooting-Noise-Layer-Simulation-for-Deep-Learning-Based-Watermarking-Netw
This is the code for paper: ``PIMoG : An Effective Screen-shooting Noise-Layer Simulation for Deep-Learning-Based Watermarking Network. .Fang, Han, et al. Proceedings of the 30th ACM International Conference on Multimedia. 2022.
ALIKE
ALIKE: Accurate and Lightweight Keypoint Detection and Descriptor Extraction
wavfile
Java Wav File IO
ISC-Track2-Submission
[NeurIPS Challenge Rank 3rd] The codes and related files to reproduce the results for Image Similarity Challenge Track 2.
ISC21-Descriptor-Track-1st
The 1st Place Solution of the Facebook AI Image Similarity Challenge (ISC21) : Descriptor Track.
AAAI22-MeCoQ
The code for the paper "Contrastive Quantization with Code Memory for Unsupervised Image Retrieval" (AAAI'22, Oral).
2019-scalingattack
Image-Scaling Attacks and Defenses
SPQ
Self-supervised Product Quantization for Deep Unsupervised Image Retrieval - ICCV2021
PRIME-augmentations
PRIME: A Few Primitives Can Boost Robustness to Common Corruptions
adversarial-attacks-pytorch
PyTorch implementation of adversarial attacks.
attack-and-defense-methods
A curated list of papers on adversarial machine learning (adversarial examples and defense methods).
ResizeRight
The correct way to resize images or tensors. For Numpy or Pytorch (differentiable).
transformer
Implementation of "Attention Is All You Need" using pytorch
2021_QQ_AIAC_Tack1_1st
QQ浏览器2021AI算法大赛赛道一 第1名 方案
DeepLearning_LHY21_Notes
深度学习 李宏毅 2021 学习笔记
transfer_adv
transfer attack; adversarial examples; black-box attack; unrestricted Adversarial Attacks on ImageNet; CVPR2021 天池黑盒竞赛
mobilevit-pytorch
A PyTorch implementation of "MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer".
volo
VOLO: Vision Outlooker for Visual Recognition
DemystifyLocalViT
Official code for paper "Demystifying Local Vision Transformer: Sparse Connectivity, Weight Sharing, and Dynamic Weight"
Attack_classification_models_with_transferability
Attack classification models with transferability, black-box attack; unrestricted adversarial attacks on imagenet, CVPR2021 安全AI挑战者计划第六期:ImageNet无限制对抗攻击 决赛第四名(team name: Advers)
Robust-Vision-Transformer
This is the implementation of our paper Towards Robust Vision Transformer
hard-label-attack
Natural Language Attacks in a Hard Label Black Box Setting.