DANCE: Enhancing saliency maps using decoys
Authors: Yang Young Lu, Wenbo Guo, Xinyu Xing, William Stafford Noble
ICML 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | To evaluate the effectiveness of DANCE, we perform extensive experiments on deep learning models that target three tasks: image classification, sentiment analysis, and network intrusion detection. |
| Researcher Affiliation | Academia | 1Department of Genome Sciences, University of Washington, Seattle, WA, USA 2College of Information Sciences and Technology, The Pennsylvania State University, State College, PA, USA 3Paul G. Allen School of Computer Science and Engineering, University of Washington, Seattle, WA, USA. |
| Pseudocode | No | The paper describes the decoy generation as an optimization problem with mathematical equations but does not present pseudocode or an algorithm block. |
| Open Source Code | Yes | The Apache licensed source code of DANCE will be available at https://bitbucket.org/noblelab/dance. |
| Open Datasets | Yes | To evaluate the effectiveness of DANCE, we first applied DANCE to randomly sampled images from the Image Net dataset (Russakovsky et al., 2015), with a pretrained VGG16 model (Simonyan & Zisserman, 2014)... To further evaluate the effectiveness of DANCE, we applied the method to randomly sampled sentences from the Stanford Sentiment Treebank (SST) (Russakovsky et al., 2015). |
| Dataset Splits | No | The paper mentions using ImageNet and SST datasets but does not explicitly provide details about specific training, validation, and test dataset splits used for its experiments. |
| Hardware Specification | No | The paper does not provide specific details about the hardware (e.g., GPU models, CPU types, memory) used for running its experiments. |
| Software Dependencies | No | The paper does not specify the version numbers of software dependencies (e.g., Python, PyTorch, CUDA, or specific libraries) used in the experiments. |
| Experiment Setup | No | The paper describes some parameters related to the DANCE framework (e.g., patch size, network layer) and evaluation metrics (e.g., K for top-K normalization) but does not provide specific training hyperparameters such as learning rates, batch sizes, or optimizer details for the deep learning models used in their experiments. |