arXiv:2104.02234
공식 코드 · Papers with Code
DeepEverest: Accelerating Declarative Top-K Queries for Deep Neural Network Interpretation
원문 초록
We design, implement, and evaluate DeepEverest, a system for the efficient execution of interpretation by example queries over the activation values of a deep neural network. DeepEverest consists of an efficient indexing technique and a query execution algorithm with various optimizations. We prove that the proposed query execution algorithm is instance optimal. Experiments with our prototype show that DeepEverest, using less than 20% of the storage of full materialization, significantly accelerates individual queries by up to 63x and consistently outperforms other methods on multi-query workloads that simulate DNN interpretation processes.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Perturbation on Feature Coalition: Towards Interpretable Deep Neural Networks
Towards More Robust Interpretation via Local Gradient Alignment
Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training
Proper Network Interpretability Helps Adversarial Robustness in Classification
An Empirical Study on the Relation between Network Interpretability and Adversarial Robustness
A brain-inspired generative model for EEG-based cognitive state identification
토론
이 논문과 연결된 포럼 글이 아직 없습니다.