quant-phNov 1, 2026

Seeing Why: Exact Evidence Maps for Quantum and Optical Image Classifiers

Authors: Teerawat Tongloy, Rangsan Jomtarak

Organizations: School of Integrated Innovative Technology, King Mongkut’s Institute of Technology Ladkrabang, Bangkok, Thailand · Faculty of Science and Technology, Suan Dusit University, Bangkok, Thailand

Abstract

When an image classifier decides, we can usually only estimate why. For quantum and all-optical classifiers that act linearly on amplitude-encoded pictures up to the measurement, with no trained classical network before or after them, each class's Born probability above its no-information share, Pg−bgP_g - b_g, splits exactly into contributions of the encoded amplitudes, shown as Born evidence maps (BEM). The split itself follows from known results on quadratic forms: with the transmitted light held fixed, it is what Integrated Gradients from a zero baseline and the Shapley value give. What we add is a way to measure it on the hardware that classifies, from class probabilities on a quantum chip or, in simulation, from camera frames on a lens bench, with no gradient circuit and no light sent backwards; a g×gg\times g map takes 1+2g21 + 2g^2 runs. Deleting the 5% of pixels with the highest evidence drops accuracy from 73% to 9% (one seed), as occlusion and gradient ×\times input do, while plain gradients remove much less. The classifiers share one architecture, a Fourier-plane mask followed by a brickwall circuit on qubits or by phase plates on a lens bench, read by a fixed Born headroom readout with no trained parameter; centring each picture on its own mean lets dark features count as much as bright ones. In simulation, four phase plates at one wavelength reach 72.3% on Caltech-10 colour photographs. On IBM's ibm_kingston, with the mask computed classically before approximate loading, 300 test pictures were classified at 37.7% against 10% chance (56.3% in exact simulation), and 2×22\times2 maps of the filtered input of 30 test pictures drawn at random in advance, measured on the chip, agreed with the exact ones (r=0.88r = 0.88; standard estimator 0.82). The maps also revealed a shortcut in the data; as the trim that removed it was chosen on test pictures, the Caltech-10 results are exploratory.

Figures & tables

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Representation Geometry and Inductive Biases in Quantum Classifiers across Classical Visual Benchmarks

    Oct 13, 2026Yu Yamaoka, Weng Ian Chan, Kosuke MitaraiQuantum Machine LearningImage Classification

  2. Image classification via a quantum-inspired strategy involving a mixture of experts

    Jul 8, 2026Kumari Jyoti, Rohith Babu, Apoorva D. PatelHybrid Quantum-Classical MLQuantum-Inspired ML

  3. Layer-wise QUBO-Based Training of CNN Classifiers for Quantum Annealing

    Mar 3, 2026Mostafa Atallah, Rebekah HerrmanImage ClassificationHybrid Quantum-Classical ML