Skip to content

Latest commit

 

History

History
175 lines (146 loc) · 13.6 KB

CHANGELOG.md

File metadata and controls

175 lines (146 loc) · 13.6 KB
Raw

Change Log

[1.2.0 Unreleased]

Summary

What's Changed

Known Issues

  • Runtime error from ONNX / OpenVINO IR models while conversion or inference for XAI in #29
  • Models not supported by white box XAI methods in #30

New Contributors

  • N/A

[1.1.0]

Summary

  • Support PyTorch models with insert_xai() API for saliency map generation on PyTorch / ONNX runtime
  • Support OpenVINO IR (.xml) / ONNX (.onnx) model files for Explainer
  • Enable AISE method: Adaptive Input Sampling for Explanation of Black-box Models
  • Add Pointing Game, Insertion-Deletion AUC and ADCC quality metrics for saliency maps
  • Upgrade OpenVINO to 2024.4.0
  • Add saliency map visualization with explanation.plot()
  • Enable flexible naming for saved saliency maps and include confidence scores
  • Add XAI method documentation

What's Changed

  • Use OVC converted models in func tests by @goodsong81 in #44
  • Update CodeCov action by @goodsong81 in #46
  • Refactor OpenVINO imports by @goodsong81 in #45
  • Support OV IR / ONNX model file for Explainer by @goodsong81 in #47
  • Try CNN -> ViT assumption for IR insertion by @goodsong81 in #48
  • Enable AISE for classification: Adaptive Input Sampling for Explanation of Black-box Models by @negvet in #49
  • Upgrade OpenVINO to 2024.3.0 by @goodsong81 in #52
  • Add saliency map visualization with explanation.plot() by @GalyaZalesskaya in #53
  • Enable flexible naming for saved saliency maps and include confidence scores by @GalyaZalesskaya in #51
  • Add Pointing Game saliency map quality metric by @GalyaZalesskaya in #54
  • Add Insertion-Deletion AUC saliency map quality metric by @GalyaZalesskaya in #56
  • Add ADCC saliency map quality metric by @GalyaZalesskaya in #57
  • Enable AISE for detection: Adaptive Input Sampling for Explanation of Black-box Models by @negvet in #55
  • Enable prediction attribute for methods that is used for enhancing saliency map overlay by @negvet in #62
  • Add documentation per-method, including summary and usage guide by @negvet in #63
  • Support Pytorch models for insert_xai API by @goodsong81 in #61
  • Auto-detect feature layer for Pytorch models by @goodsong81 in #64
  • Upgrade OpenVINO to 2024.4.0 by @goodsong81 in #72

Known Issues

  • Runtime error from ONNX / OpenVINO IR models while conversion or inference for XAI in #29
  • Models not supported by white box XAI methods in #30

New Contributors

  • N/A

[1.0.0]

Summary

  • Support generation of classification and detection per-class and per-image saliency maps
  • Enable White-Box (ReciproCAM) and Black-Box (RISE) eXplainable AI algorithms
  • Support CNNs and Transformer-based architectures (validation on diverse set of timm models)
  • Enable Explainer (stateful object) as the main interface for XAI algorithms
  • Support AUTO mode by default to detect the best XAI method for given models
  • Expose insert_xai functional API to support XAI head insertion for OpenVINO IR models

What's Changed

Known Issues

  • Runtime error from ONNX / OpenVINO IR models while conversion or inference for XAI in #29
  • Models not supported by white box XAI methods in #30

New Contributors