4D and Quantum Vision / VCAI Department

Quantum Computer Vision and Machine Learning (QCVML)

Seminar – Winter Semester 23/24

Organiser: Dr. Vladislav Golyanik

Organisation | Content | Format | Resources


CCuantuMM: Cycle-Consistent Quantum-Hybrid Matching of Multiple Shapes CVPR, 2023	QuAnt: Quantum Annealing with Learnt Couplings ICLR, 2023

Overview

Computer Vision strives to develop algorithms for understanding, interpreting and reconstructing information about real-world scenes from image and video data.

Machine Learning is concerned with studying and developing algorithms which use statistical models to solve problems by analyzing and drawing inference from data.

Quantum Computing focuses on leveraging quantum computational paradigms in algorithm development (e.g., in computer vision and machine learning).

Computer vision (CV) studies the automatic processing of visual and spatial information in the form of 2D images, depth maps, 3D point clouds, and different combinations of those (possibly along with other sensory signals). The long-term aim of computer vision is inspired by the capabilities of the human visual system (HVS) to come up with intelligent and high-level interpretations of the observed scenes. It manifests a tight intertwining between CV and machine learning (ML): While modern CV strongly relies on ML techniques, developments in ML are often driven by challenging CV problems.

A quantum computer (QC) is a computing machine which takes advantage of quantum effects such as quantum superposition, entanglement, tunnelling and contextuality to solve problems notoriously difficult (belonging to challenging complexity classes such as NP) for a classical computer. Thanks to the exponentially increasing investment in the technology, quantum computers are gradually moving from the realms of theory towards actual devices. Albeit restricted, experimental realisations of numerous quantum algorithms have demonstrated improved computational performance bringing the community closer to the desired supremacy in recent years.

The aforementioned premises of quantum computing and annealing has led to the popularisation of quantum computer vision (QCV), where researchers started to port existing computer vision problems into forms amenable to quantum computation. However, reframing the existing problems in the context of this new computing paradigm is not trivial. For instance, existing literature relaxes most of the (discrete) combinatorial search problems to continuous ones, whereas quantum annealing is great at optimisation on discrete binary variables. Hence, oftentimes we are required to revise the problem formulations at hand altogether. As one of the most massively data-producing disciplines, computer vision could become a particular profiteer from QC.

This seminar series will cover advanced research topics that cross the boundaries between the fields of Computer Vision, Machine Learning and Quantum Computing. Specifically, we will cover research papers on the following areas:

Quantum-inspired methods
Point set and mesh alignment
Motion segmentation
Robust model fitting
Object tracking
Neural network training
Quantum-classical optimisation
Quantum Machine Learning (QML)
Quantum Convolutional Neural Networks (QCNNs)
Recurrent Quantum Neural Networks (R-QNNs)
Quantum Approximate Optimization Algorithm (QAOA)

Topics (Preliminary Selection)

The following table lists more topics than available weeks – this is to allow some flexibility for the interests of the group to change the course structure. Once every participant has submitted their choice of topics, this list will be updated to show the presenter of each topic. Send us an email if you cannot access a paper for some reason.

Click on each topic to show the papers to be discussed or show all papers hide all papers.

Topic and Papers	Presentation
Graph Matching and Permutation Synchronisation Adiabatic Quantum Graph Matching with Permutation Matrix Constraints Benkner et al. 3DV 2020 Quantum Permutation Synchronization Birdal et al. CVPR 2021	Date: TBD Presenter: TBD
Object Tracking Quantum-Soft QUBO Suppression for Accurate Object Detection Li and Ghosh ECCV 2020 Adiabatic Quantum Computing for Multi Object Tracking Zaech et al. CVPR 2022	Date: TBD Presenter: TBD
Frank-Wolfe Algorithm Revisiting Frank-Wolfe: Projection-Free Sparse Convex Optimization Jaggi ICML 2013 Q-FW: A Hybrid Classical-Quantum Frank-Wolfe for Quadratic Binary Optimization Yurtsever et al. ECCV 2022	Date: TBD Presenter: TBD
Motion Segmentation Robust Motion Segmentation From Pairwise Matches Arrigoni and Pajdla ICCV 2019 Quantum Motion Segmentation Arrigoni et al. ECCV 2022	Date: TBD Presenter: TBD
Mesh Alignment Q-Match: Iterative Shape Matching via Quantum Annealing Benkner et al. ICCV 2021 CCuantuMM: Cycle-Consistent Quantum-Hybrid Matching of Multiple Shapes Bhatia et al. CVPR 2023	Date: TBD Presenter: TBD
Robust Fitting/Regression A Hybrid Quantum-Classical Algorithm for Robust Fitting Doan et al. CVPR 2021 Quantum Multi-Model Fitting Farina et al. CVPR 2023	Date: TBD Presenter: TBD
Transformation Estimation Matching Point Sets with Quantum Circuit Learning Noormandipour and Wang ICASSP 2022 An Iterative Quantum Approach for Transformation Estimation From Point Sets Meli et al. CVPR 2022	Date: TBD Presenter: TBD
Adiabatic Quantum Computing + Machine Learning Quantum Annealing Formulation for Binary Neural Networks Sasdelli and Chin DICTA 2021 QuAnt: Quantum Annealing with Learnt Couplings Benkner et al. ICLR 2023	Date: TBD Presenter: TBD
QML Theory Expressibility and Entangling Capability of Parameterized Quantum Circuits for Hybrid Quantum-classical Algorithms Sim et al. Advanced Quantum Technologies 2019 Supervised Learning with Quantum-enhanced Feature Spaces Havlíček et al. Nature 2019	Date: TBD Presenter: TBD
Quantum Approximate Optimization Algorithm (QAOA) Quantum Approximate Optimization Algorithm: Performance, Mechanism, and Implementation on Near-Term Devices Zhou et al. Phys. Rev. X, 2020 A Universal Quantum Algorithm for Weighted Maximum Cut and Ising Problems Meli et al. ArXiv 2023	Date: TBD Presenter: TBD
Quantum Convolutional Neural Networks (QCNNs) Quantum Convolutional Neural Networks Cong et al. Nature Physics, 2019 A Hybrid Quantum-Classical Approach based on the Hadamard Transform for the Convolutional Layer Pan et al. ArXiv, 2023	Date: TBD Presenter: TBD
Advanced QML Algorithms Recurrent Quantum Neural Networks Bausch NeurIPS 2020 Quantum Self-Supervised Learning Jaderberg et al. Quantum Science and Technology, 2022	Date: TBD Presenter: TBD