30 skills found
castorini / DaamDiffusion attentive attribution maps for interpreting Stable Diffusion.
marcoancona / DeepExplainA unified framework of perturbation and gradient-based attribution methods for Deep Neural Networks interpretability. DeepExplain also includes support for Shapley Values sampling. (ICLR 2018)
yulongwang12 / Visual AttributionPytorch Implementation of recent visual attribution methods for model interpretability
fredhohman / Summit🏔️ Summit: Scaling Deep Learning Interpretability by Visualizing Activation and Attribution Summarizations
LLM-Interp / CLT ForgeA Mechanistic Interpretability Toolkit for Cross-Layer Transcoder Training and Attribution-Graph Visualization
YingWANGG / M2IBCode for the paper Visual Explanations of Image–Text Representations via Multi-Modal Information Bottleneck Attribution
CherBass / ICAMICAM: Interpretable Classification via Disentangled Representations and Feature Attribution Mapping
mtsang / ArchipelagoOfficial Code Repo for the Paper: "How does This Interaction Affect Me? Interpretable Attribution for Feature Interactions", In NeurIPS 2020
csinva / Disentangled Attribution CurvesUsing / reproducing DAC from the paper "Disentangled Attribution Curves for Interpreting Random Forests and Boosted Trees"
fengyanzi / Local Attribution Map For Super ResolutionThe Local Attribution Map (LAM) is an interpretability tool for super-resolution reconstruction tasks. 局部归因图（Local Attribution Map，LAM）是一种用于超分辨率重建任务的诊断工具。
fredhohman / Summit NotebooksNotebooks for Scaling Deep Learning Interpretability by Visualizing Activation and Attribution Summarizations
ChenQian0618 / SHEPThe open-source code of "CS-SHAP: Extending SHAP to "SHapley Estimated Explanation (SHEP): A Fast post-hoc attribution method for interpreting Intelligent Fault Diagnosis".
deezer / Interpretable Nn AttributionSource code from our RecSys 2020 paper: "Making neural network interpretable with attribution: application to implicit signals prediction" (D. Afchar, R. Hennequin)
anilprakash94 / IsanregAn Interpretable Self-Attention Network with block-attention and attention-attribution.
Cra2yDavid / PowerformerPowerformer: A Section-adaptive Transformer for Power Flow Adjustment
RuoyuChen10 / LIMALess is More: Efficient Black-box Attribution via Minimal Interpretable Subset Selection
fanny-jourdan / Cockatiel🦜Code for paper: "COCKATIEL: COntinuous Concept ranKed ATtribution with Interpretable ELements for explaining neural net classifiers on NLP" (ACL 2023 Findings)
dongdyang / Interpretable Deep Model MtaThis is the project that developed for marketing attribution. It is an interpretable deep learning model for marketing problem.
fursovia / Tcav Nlp"Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)" paper implementation
yushundong / BINDOpen-source code for "Interpreting Unfairness in Graph Neural Networks via Training Node Attribution".
