4 citations · 6 across the 11 of their papers we have counts for
6 papers · 1 filter
Geo-vision: Native-Resolution Geometry and Sampled Topology for Vehicle-Part Damage Classification
Usef Faghihi, Amir Saki, Serge Jonathan Kogbeti-Wongo
Geo-vision classifies vehicle-part damage using a fixed representation combining appearance, multiscale geometry, orientation, and sampled digital topology. Connected components, h…
Common-Witness Certificates and Sharp Feature Bounds for Counterfactual Image Auditing
Usef Faghihi, Amir Saki
An image editor may satisfy every regional plausibility constraint separately even when no single latent explanation fits the complete output. We formalize this local-to-global fai…
Causal inference for group-contaminated structured outcomes: observable quotients, lossless reduction and exact randomization inference
Usef Faghihi, Amir Saki
Structured potential outcomes such as microscopy images may be recorded after an unknown, unit-specific transformation. If that transformation can depend on treatment, covariates o…
Topological Ignorability for Structural Causal Effects Beyond Means
Usef Faghihi
Many interventions alter the structure of an outcome distribution rather than its mean: they can split a population into disconnected regimes, create loops or holes, generate branc…
Global and Local Topology-Aware Attention with Persistent Homology and Euler Biases for Time-Series Forecasting
Usef Faghihi, Amir Saki
Scientific time series often encode predictive geometric structure, including connectivity, cycles, shell-like geometry, directional changes, and nonlinear neighborhoods, that stan…
Beyond Means: Topological Causal Effects under Persistent-Homology Ignorability
Amir Saki, Usef Faghihi
Average treatment effects (ATE) and conditional average treatment effects (CATE) are foundational causal estimands, but they target changes in expected outcomes and can miss treatm…