oneTaken/awesome_deep_learning_interpretability
A curated collection of high-citation research papers on deep learning model interpretability and explainability from top ML/CV conferences.
★767 stars Learning
Velocity · 7d
+0.3
★ / day
Trend
→steady
star history
This repository collects academic papers on neural network interpretability, organized by publication venue and citation count. It covers explainability methods for deep learning models including convolutional networks and NLP models. The collection spans top-tier venues like CVPR, ICLR, NeurIPS, and includes links to implementations where available.