https://github.com/AkhilanB/Proper-Interpretability
공식 코드Proper Network Interpretability Helps Adversarial Robustness in Classification
Papers with Code 아카이브
Network Interpretation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/a1noack/interp_regularization
공식 코드An Empirical Study on the Relation between Network Interpretability and Adversarial Robustness
https://github.com/joshua840/robustaga
공식 코드Towards More Robust Interpretation via Local Gradient Alignment
https://github.com/salesforce/lavis
공식 코드Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training
https://github.com/teriri1999/perturebation-on-feature-coalition
공식 코드Perturbation on Feature Coalition: Towards Interpretable Deep Neural Networks
https://github.com/uwdb/DeepEverest
공식 코드DeepEverest: Accelerating Declarative Top-K Queries for Deep Neural Network Interpretation
https://github.com/GeondoPark/attribute-preserve
Attribution Preservation in Network Compression for Reliable Network Interpretation
https://github.com/IanWangg/NeurlPS-Reproduce-Chanllenge
Fooling Neural Network Interpretations via Adversarial Model Manipulation
https://github.com/Tzoulio/Large_Models_Dialogue_for_Active_Perception
Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training
https://github.com/abril4416/kgen_vqa
Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training
https://github.com/nikhil-krishna/NeurIPS-Reproducibility-Challenge
Fooling Neural Network Interpretations via Adversarial Model Manipulation
https://github.com/rmrisforbidden/Fooling_Neural_Network-Interpretations
Fooling Neural Network Interpretations via Adversarial Model Manipulation
https://github.com/xpixelgroup/rdsr
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.