Paper Reading AI Learner

Evaluation of Interpretability Methods and Perturbation Artifacts in Deep Neural Networks

2022-03-06 10:14:09
Lennart Brocki, Neo Christopher Chung

Abstract

The challenge of interpreting predictions from deep neural networks has prompted the development of numerous interpretability methods. Many of interpretability methods attempt to quantify the importance of input features with respect to the class probabilities, and are called importance estimators or saliency maps. A popular approach to evaluate such interpretability methods is to perturb input features deemed important for predictions and observe the decrease in accuracy. However, perturbation-based evaluation methods may confound the sources of accuracy degradation. We conduct computational experiments that allow to empirically estimate the $\textit{fidelity}$ of interpretability methods and the contribution of perturbation artifacts. All considered importance estimators clearly outperform a random baseline, which contradicts the findings of ROAR [arXiv:1806.10758]. We further compare our results to the crop-and-resize evaluation framework [arXiv:1705.07857], which are largely in agreement. Our study suggests that we can estimate the impact of artifacts and thus empirically evaluate interpretability methods without retraining.

Abstract (translated)

URL

https://arxiv.org/abs/2203.02928

PDF

https://arxiv.org/pdf/2203.02928.pdf


Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot