Muhammad Rashid

Muhammad Rashid

Machine Learning Researcher

Talks and presentations

ShapBPT: Image feature attributions using Data-Aware Binary Partition Trees

January 25, 2026

Talk, Singapore Expo Center, Singapore

Pixel-level feature attributions play a key role in Explainable Computer Vision (XCV) by revealing how visual features influence model predictions. While hierarchical Shapley methods based on the Owen formula offer a principled explanation framework, existing approaches overlook the multiscale and morphological structure of images, resulting in inefficient computation and weak semantic alignment.

Can I trust my anomaly detection system? A case study based on explainable AI

July 17, 2024

Talk, Mediterranean Conference Centre, La Valletta, Malta

Generative models based on variational autoencoders are a popular technique for detecting anomalies in images in a semi-supervised context. A common approach employs the anomaly score to detect the presence of anomalies, and it is known to reach high level of accuracy on benchmark datasets. However, since anomaly scores are computed from reconstruction disparities, they often obscure the detection of various spurious features, raising concerns regarding their actual efficacy. This case study explores the robustness of an anomaly detection system based on variational autoencoder generative models through the use of eXplainable AI methods. The goal is to get a different perspective on the real performances of anomaly detectors that use reconstruction differences. In our case study we discovered that, in many cases, samples are detected as anomalous for the wrong or misleading factors.

Using Stratified Sampling to Improve LIME Image Explanations

February 21, 2024

Talk, Vancouver Convention Centre, Vancouver, Canada

We investigate the use of a stratified sampling approach for LIME Image, a popular model-agnostic explainable AI method for computer vision tasks, in order to reduce the artifacts generated by typical Monte Carlo sampling. Such artifacts are due to the undersampling of the dependent variable in the synthetic neighborhood around the image being explained, which may result in inadequate explanations due to the impossibility of fitting a linear regressor on the sampled data. We then highlight a connection with the Shapley theory, where similar arguments about undersampling and sample relevance were suggested in the past. We derive all the formulas and adjustment factors required for an unbiased stratified sampling estimator. Experiments show the efficacy of the proposed approach..