Muhammad Rashid

Muhammad Rashid

Machine Learning Researcher

Muhammad Rashid

Machine Learning Researcher specializing in Explainable AI (XAI), Computer Vision, and Visual Anomaly Detection for real-world and safety-critical systems.

Research Focus

  • Explainable AI for trustworthy decision-making
  • Visual anomaly detection in industrial and robotic environments
  • Pixel-level feature attribution using Shapley-based methods
  • Robust and efficient explanation methods for computer vision

šŸ“Œ AAAI 2026: ShapBPT ā€” Image Feature Attribution using Data-Aware Binary Partition Trees
šŸ“Œ ICPE 2026 / QualITA Workshop: ShapBPT in Perspective: A Consolidated Review and an eXplainable Anomaly Detection Case Study

Systems & Engineering

  • Real-time anomaly detection for robotics safety
  • ROS2-based live inference pipeline
  • VAE / VAE-GAN models for industrial anomaly detection
  • Multi-camera monitoring and safety-area segmentation
  • End-to-end workflow: training ā†’ threshold calibration ā†’ live deployment

Achieved:

  • ~12 FPS real-time inference
  • ~99.6% detection accuracy in industrial scenarios
  • Explainable anomaly maps for safety-critical decision support

Open Source & Tools

  • ShapBPT ā€” AAAI 2026 explainability framework
  • XAD ā€” Explainable anomaly detection with ShapBPT
  • LIME Stratified Sampling ā€” Improved explanation stability
  • AI on Edge Devices ā€” Lightweight deployment pipelines
  • XAI evaluation tools for saliency, attribution, and benchmarking

Selected Publications

ShapBPT: Image Feature Attribution using Data-Aware Binary Partition Trees

AAAI 2026

PDF arXiv Code Tests PyPI Docs User Study Poster

ShapBPT in Perspective: A Consolidated Review and an eXplainable Anomaly Detection Case Study

QualITA Workshop, ICPE 2026

Paper Code

Using Stratified Sampling to Improve LIME Image Explanations

AAAI 2024

Paper Code Tests PyPI Slides

Can I Trust My Anomaly Detection System?

XAI World 2024

arXiv Code

āž”ļø See full publication list

šŸ”§ Real-Time Anomaly Detection for Robotics

  • Industrial safety monitoring system
  • Multi-area detection: RoboArm, Conveyor Belt, Pallet Left, Pallet Right
  • ROS2 integration with live inference and anomaly scoring
  • Visual anomaly maps for decision interpretation

Project Page Code

ShapBPT

  • AAAI 2026 explainability method for images
  • Uses data-aware Binary Partition Trees
  • Provides hierarchical Shapley-based feature attributions
  • More image-structure-aware than standard SHAP partition explainer

PDF arXiv Code Tests PyPI Docs User Study Poster

XAD: Explainable Anomaly Detection

  • Applies ShapBPT to anomaly detection systems
  • Explains why an image or region is considered anomalous
  • Supports interpretation of black-box anomaly detection models

Code

LIME Stratified Sampling

  • Improves stability of LIME image explanations
  • Reduces variance in perturbation-based sampling
  • Provides more reliable local explanations

āž”ļø View all projects

šŸŒ Experience

  • šŸŽ“ PhD Researcher ā€” University of Turin, Italy
  • šŸ­ Industrial Research ā€” RuleX Innovation Labs
  • šŸ‡ŖšŸ‡ŗ EU Project ā€” DistriMuSe: Robotics Safety & AI
  • šŸŒ Visiting Researcher ā€” University of Granada, Spain

Collaboration

Iā€™m interested in collaborations on:

  • Explainable AI and trustworthy machine learning
  • Visual anomaly detection
  • Industrial AI and robotics safety
  • Computer vision for real-world systems
  • Vision-language models and explainability

Contact