Papers with Code 아카이브
DNN Testing
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
Testing the reliability of DNNs.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
GAN-enhanced Simulation-driven DNN Testing in Absence of Ground Truth
DANDI: Diffusion as Normative Distribution for Deep Neural Network Input
Bridging the Gap between Real-world and Synthetic Images for Testing Autonomous Driving Systems
Targeted Deep Learning System Boundary Testing
DeepSample: DNN sampling-based testing for operational accuracy assessment
DeepKnowledge: Generalisation-Driven Deep Learning Testing
Rethinking Diversity in Deep Neural Network Testing
CGDTest: A Constrained Gradient Descent Algorithm for Testing Neural Networks
An Overview of Structural Coverage Metrics for Testing Neural Networks
NPC: Neuron Path Coverage via Characterizing Decision Logic of Deep Neural Networks
CatchBackdoor: Backdoor Detection via Critical Trojan Neural Path Fuzzing
Black-Box Testing of Deep Neural Networks Through Test Case Diversity
Revisiting Neuron Coverage for DNN Testing: A Layer-Wise and Distribution-Aware Criterion
Provably Valid and Diverse Mutations of Real-World Media Data for DNN Testing
Exposing Previously Undetectable Faults in Deep Neural Networks
Neuron Coverage-Guided Domain Generalization
Distribution-Aware Testing of Neural Networks Using Generative Models
IWA: Integrated Gradient based White-box Attacks for Fooling Deep Neural Networks
Towards Practical Robustness Analysis for DNNs based on PAC-Model Learning
Automatic Test Suite Generation for Key-Points Detection DNNs using Many-Objective Search (Experience Paper)
Comparing Offline and Online Testing of Deep Neural Networks: An Autonomous Car Case Study
Boosting Operational DNN Testing Efficiency through Conditioning
Testing DNN Image Classifiers for Confusion & Bias Errors
DeepFault: Fault Localization for Deep Neural Networks
DeepBillboard: Systematic Physical-World Testing of Autonomous Driving Systems
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.