https://github.com/gandolfczjh/3d2fool
Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patches
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patches
U-Net: Convolutional Networks for Biomedical Image Segmentation
SNIP: Single-shot Network Pruning based on Connection Sensitivity
Decoupling Classifier for Boosting Few-shot Object Detection and Instance Segmentation
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation
EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis
U-Net: Convolutional Networks for Biomedical Image Segmentation
U-Net: Convolutional Networks for Biomedical Image Segmentation
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
R-FCN: Object Detection via Region-based Fully Convolutional Networks
Rethinking Atrous Convolution for Semantic Image Segmentation
Learning Transferable Visual Models From Natural Language Supervision
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.