Search

Gate quantum computers generate significant interest due to their potential to solve certain difficult problems such as prime factorization in polynomial time. Computer vision researchers have long been attracted to the power of quantum computers. Robust fitting, which is fundamentally important to many computer vision pipelines, has recently been shown to be amenable to gate quantum computing. The previous proposed solution was to compute Boolean influence as a measure of outlyingness using the Bernstein-Vazirani quantum circuit. However, the method assumed a quantum implementation of an $\ell_\infty$ feasibility test, which has not been demonstrated. In this paper, we take a big stride towards quantum robust fitting: we propose a quantum circuit to solve the $\ell_\infty$ feasibility test in the 1D case, which allows to demonstrate for the first time quantum robust fitting on a real gate quantum computer, the IonQ Aria. We also show how 1D Boolean influences can be accumulated to compute Boolean influences for higher-dimensional non-linear models, which we experimentally validate on real benchmark datasets., Comment: Accepted by the European Conference on Computer Vision 2024 (ECCV2024) as Oral. The paper is written for a computer vision audience who generally has minimal quantum physics background

We present, QP-SBGD, a novel layer-wise stochastic optimiser tailored towards training neural networks with binary weights, known as binary neural networks (BNNs), on quantum hardware. BNNs reduce the computational requirements and energy consumption of deep learning models with minimal loss in accuracy. However, training them in practice remains to be an open challenge. Most known BNN-optimisers either rely on projected updates or binarise weights post-training. Instead, QP-SBGD approximately maps the gradient onto binary variables, by solving a quadratic constrained binary optimisation. Under practically reasonable assumptions, we show that this update rule converges with a rate of $\mathcal{O}(1 / \sqrt{T})$. Moreover, we show how the $\mathcal{NP}$-hard projection can be effectively executed on an adiabatic quantum annealer, harnessing recent advancements in quantum computation. We also introduce a projected version of this update rule and prove that if a fixed point exists in the binary variable space, the modified updates will converge to it. Last but not least, our algorithm is implemented layer-wise, making it suitable to train larger networks on resource-limited quantum hardware. Through extensive evaluations, we show that QP-SBGD outperforms or is on par with competitive and well-established baselines such as BinaryConnect, signSGD and ProxQuant when optimising the Rosenbrock function, training BNNs as well as binary graph neural networks.

A successful application of quantum annealing to machine learning is training restricted Boltzmann machines (RBM). However, many neural networks for vision applications are feedforward structures, such as multilayer perceptrons (MLP). Backpropagation is currently the most effective technique to train MLPs for supervised learning. This paper aims to be forward-looking by exploring the training of MLPs using quantum annealers. We exploit an equivalence between MLPs and energy-based models (EBM), which are a variation of RBMs with a maximum conditional likelihood objective. This leads to a strategy to train MLPs with quantum annealers as a sampling engine. We prove our setup for MLPs with sigmoid activation functions and one hidden layer, and demonstrated training of binary image classifiers on small subsets of the MNIST and Fashion-MNIST datasets using the D-Wave quantum annealer. Although problem sizes that are feasible on current annealers are limited, we obtained comprehensive results on feasible instances that validate our ideas. Our work establishes the potential of quantum computing for training MLPs., Comment: 22 pages, 15 figures

The availability of representative datasets is an essential prerequisite for many successful artificial intelligence and machine learning models. However, in real life applications these models often encounter scenarios that are inadequately represented in the data used for training. There are various reasons for the absence of sufficient data, ranging from time and cost constraints to ethical considerations. As a consequence, the reliable usage of these models, especially in safety-critical applications, is still a tremendous challenge. Leveraging additional, already existing sources of knowledge is key to overcome the limitations of purely data-driven approaches. Knowledge augmented machine learning approaches offer the possibility of compensating for deficiencies, errors, or ambiguities in the data, thus increasing the generalization capability of the applied models. Even more, predictions that conform with knowledge are crucial for making trustworthy and safe decisions even in underrepresented scenarios. This work provides an overview of existing techniques and methods in the literature that combine data-driven models with existing knowledge. The identified approaches are structured according to the categories knowledge integration, extraction and conformity. In particular, we address the application of the presented methods in the field of autonomous driving., Comment: 111 pages, Added section on Run-time Network Verification

Many applications in image-guided surgery and therapy require fast and reliable non-linear, multi-modal image registration. Recently proposed unsupervised deep learning-based registration methods have demonstrated superior performance compared to iterative methods in just a fraction of the time. Most of the learning-based methods have focused on mono-modal image registration. The extension to multi-modal registration depends on the use of an appropriate similarity function, such as the mutual information (MI). We propose guiding the training of a deep learning-based registration method with MI estimation between an image-pair in an end-to-end trainable network. Our results show that a small, 2-layer network produces competitive results in both mono- and multi-modal registration, with sub-second run-times. Comparisons to both iterative and deep learning-based methods show that our MI-based method produces topologically and qualitatively superior results with an extremely low rate of non-diffeomorphic transformations. Real-time clinical application will benefit from a better visual matching of anatomical structures and less registration failures/outliers., Comment: 4 pages, 4 figures, 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), oral presentation

Fitting geometric models onto outlier contaminated data is provably intractable. Many computer vision systems rely on random sampling heuristics to solve robust fitting, which do not provide optimality guarantees and error bounds. It is therefore critical to develop novel approaches that can bridge the gap between exact solutions that are costly, and fast heuristics that offer no quality assurances. In this paper, we propose a hybrid quantum-classical algorithm for robust fitting. Our core contribution is a novel robust fitting formulation that solves a sequence of integer programs and terminates with a global solution or an error bound. The combinatorial subproblems are amenable to a quantum annealer, which helps to tighten the bound efficiently. While our usage of quantum computing does not surmount the fundamental intractability of robust fitting, by providing error bounds our algorithm is a practical improvement over randomised heuristics. Moreover, our work represents a concrete application of quantum computing in computer vision. We present results obtained using an actual quantum computer (D-Wave Advantage) and via simulation. Source code: https://github.com/dadung/HQC-robust-fitting, Comment: IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR) 2022

Data collected by Earth-observing (EO) satellites are often afflicted by cloud cover. Detecting the presence of clouds -- which is increasingly done using deep learning -- is crucial preprocessing in EO applications. In fact, advanced EO satellites perform deep learning-based cloud detection on board the satellites and downlink only clear-sky data to save precious bandwidth. In this paper, we highlight the vulnerability of deep learning-based cloud detection towards adversarial attacks. By optimising an adversarial pattern and superimposing it into a cloudless scene, we bias the neural network into detecting clouds in the scene. Since the input spectra of cloud detectors include the non-visible bands, we generated our attacks in the multispectral domain. This opens up the potential of multi-objective attacks, specifically, adversarial biasing in the cloud-sensitive bands and visual camouflage in the visible bands. We also investigated mitigation strategies against the adversarial attacks. We hope our work further builds awareness of the potential of adversarial attacks in the EO community.

Deep neural networks (DNNs) have become essential for processing the vast amounts of aerial imagery collected using earth-observing satellite platforms. However, DNNs are vulnerable towards adversarial examples, and it is expected that this weakness also plagues DNNs for aerial imagery. In this work, we demonstrate one of the first efforts on physical adversarial attacks on aerial imagery, whereby adversarial patches were optimised, fabricated and installed on or near target objects (cars) to significantly reduce the efficacy of an object detector applied on overhead images. Physical adversarial attacks on aerial images, particularly those captured from satellite platforms, are challenged by atmospheric factors (lighting, weather, seasons) and the distance between the observer and target. To investigate the effects of these challenges, we devised novel experiments and metrics to evaluate the efficacy of physical adversarial attacks against object detectors in aerial scenes. Our results indicate the palpable threat posed by physical adversarial attacks towards DNNs for processing satellite imagery.

Quantum annealing is a promising paradigm for building practical quantum computers. Compared to other approaches, quantum annealing technology has been scaled up to a larger number of qubits. On the other hand, deep learning has been profoundly successful in pushing the boundaries of AI. It is thus natural to investigate potentially game changing technologies such as quantum annealers to augment the capabilities of deep learning. In this work, we explore binary neural networks, which are lightweight yet powerful models typically intended for resource constrained devices. Departing from current training regimes for binary networks that smooth/approximate the activation functions to make the network differentiable, we devise a quadratic unconstrained binary optimization formulation for the training problem. While the problem is intractable, i.e., the cost to estimate the binary weights scales exponentially with network size, we show how the problem can be optimized directly on a quantum annealer, thereby opening up to the potential gains of quantum computing. We experimentally validated our formulation via simulation and testing on an actual quantum annealer (D-Wave Advantage), the latter to the extent allowable by the capacity of current technology., Comment: 13 pages, 4 figures

We test the adequacy of ultraviolet (UV) spectra for characterizing the outer structure of Type Ia supernova (SN) ejecta. For this purpose, we perform spectroscopic analysis for ASASSN-14lp, a normal SN Ia showing low continuum in the mid-UV regime. To explain the strong UV suppression, two possible origins have been investigated by mapping the chemical profiles over a significant part of their ejecta. We fit the spectral time series with mid-UV coverage obtained before and around maximum light by HST, supplemented with ground-based optical observations for the earliest epochs. The synthetic spectra are calculated with the one dimensional MC radiative-transfer code TARDIS from self-consistent ejecta models. Among several physical parameters, we constrain the abundance profiles of nine chemical elements. We find that a distribution of $^{56}$Ni (and other iron-group elements) that extends toward the highest velocities reproduces the observed UV flux well. The presence of radioactive material in the outer layers of the ejecta, if confirmed, implies strong constraints on the possible explosion scenarios. We investigate the impact of the inferred $^{56}$Ni distribution on the early light curves with the radiative transfer code TURTLS, and confront the results with the observed light curves of ASASSN-14lp. The inferred abundances are not in conflict with the observed photometry. We also test whether the UV suppression can be reproduced if the radiation at the photosphere is significantly lower in the UV regime than the pure Planck function. In this case, solar metallicity might be sufficient enough at the highest velocities to reproduce the UV suppression., Comment: 18 pages, 16 figures, accepted for publication in MNRAS

Generalised zero-shot learning (GZSL) is a classification problem where the learning stage relies on a set of seen visual classes and the inference stage aims to identify both the seen visual classes and a new set of unseen visual classes. Critically, both the learning and inference stages can leverage a semantic representation that is available for the seen and unseen classes. Most state-of-the-art GZSL approaches rely on a mapping between latent visual and semantic spaces without considering if a particular sample belongs to the set of seen or unseen classes. In this paper, we propose a novel GZSL method that learns a joint latent representation that combines both visual and semantic information. This mitigates the need for learning a mapping between the two spaces. Our method also introduces a domain classification that estimates whether a sample belongs to a seen or an unseen class. Our classifier then combines a class discriminator with this domain classifier with the goal of reducing the natural bias that GZSL approaches have toward the seen classes. Experiments show that our method achieves state-of-the-art results in terms of harmonic mean, the area under the seen and unseen curve and unseen classification accuracy on public GZSL benchmark data sets. Our code will be available upon acceptance of this paper.

Generalised zero-shot learning (GZSL) methods aim to classify previously seen and unseen visual classes by leveraging the semantic information of those classes. In the context of GZSL, semantic information is non-visual data such as a text description of both seen and unseen classes. Previous GZSL methods have utilised transformations between visual and semantic embedding spaces, as well as the learning of joint spaces that include both visual and semantic information. In either case, classification is then performed on a single learned space. We argue that each embedding space contains complementary information for the GZSL problem. By using just a visual, semantic or joint space some of this information will invariably be lost. In this paper, we demonstrate the advantages of our new GZSL method that combines the classification of visual, semantic and joint spaces. Most importantly, this ensembling allows for more information from the source domains to be seen during classification. An additional contribution of our work is the application of a calibration procedure for each classifier in the ensemble. This calibration mitigates the problem of model selection when combining the classifiers. Lastly, our proposed method achieves state-of-the-art results on the CUB, AWA1 and AWA2 benchmark data sets and provides competitive performance on the SUN data set.

Accurately and rapidly classifying exoplanet candidates from transit surveys is a goal of growing importance as the data rates from space-based survey missions increases. This is especially true for NASA's TESS mission which generates thousands of new candidates each month. Here we created the first deep learning model capable of classifying TESS planet candidates. We adapted the neural network model of Ansdell et al. (2018) to TESS data. We then trained and tested this updated model on 4 sectors of high-fidelity, pixel-level simulations data created using the Lilith simulator and processed using the full TESS SPOC pipeline. We find our model performs very well on our simulated data, with 97% average precision and 92% accuracy on planets in the 2-class model. This accuracy is also boosted by another ~4% if planets found at the wrong periods are included. We also performed 3- and 4-class classification of planets, blended & target eclipsing binaries, and non-astrophysical false positives, which have slightly lower average precision and planet accuracies, but are useful for follow-up decisions. When applied to real TESS data, 61% of TCEs coincident with currently published TOIs are recovered as planets, 4% more are suggested to be EBs, and we propose a further 200 TCEs as planet candidates., Comment: 11 pages, 10 figures, Submitted to A&A

In this paper, we introduce a variation of a state-of-the-art real-time tracker (CFNet), which adds to the original algorithm robustness to target loss without a significant computational overhead. The new method is based on the assumption that the feature map can be used to estimate the tracking confidence more accurately. When the confidence is low, we avoid updating the object's position through the feature map; instead, the tracker passes to a single-frame failure mode, during which the patch's low-level visual content is used to swiftly update the object's position, before recovering from the target loss in the next frame. The experimental evidence provided by evaluating the method on several tracking datasets validates both the theoretical assumption that the feature map is associated to tracking confidence, and that the proposed implementation can achieve target recovery in multiple scenarios, without compromising the real-time performance., Comment: arXiv admin note: substantial text overlap with arXiv:1806.07844

Generalized zero shot learning (GZSL) is defined by a training process containing a set of visual samples from seen classes and a set of semantic samples from seen and unseen classes, while the testing process consists of the classification of visual samples from seen and unseen classes. Current approaches are based on testing processes that focus on only one of the modalities (visual or semantic), even when the training uses both modalities (mostly for regularizing the training process). This under-utilization of modalities, particularly during testing, can hinder the classification accuracy of the method. In addition, we note a scarce attention to the development of learning methods that explicitly optimize a balanced performance of seen and unseen classes. Such issue is one of the reasons behind the vastly superior classification accuracy of seen classes in GZSL methods. In this paper, we mitigate these issues by proposing a new GZSL method based on multi-modal training and testing processes, where the optimization explicitly promotes a balanced classification accuracy between seen and unseen classes. Furthermore, we explore Bayesian inference for the visual and semantic classifiers, which is another novelty of our work in the GZSL framework. Experiments show that our method holds the state of the art (SOTA) results in terms of harmonic mean (H-mean) classification between seen and unseen classes and area under the seen and unseen curve (AUSUC) on several public GZSL benchmarks., Comment: 10 pages, 3 Figures, 4 Tables

In this paper, we present a method for instance ranking and retrieval at fine-grained level based on the global features extracted from a multi-attribute recognition model which is not dependent on landmarks information or part-based annotations. Further, we make this architecture suitable for mobile-device application by adopting the bilinear CNN to make the multi-attribute recognition model smaller (in terms of the number of parameters). The experiments run on the Dress category of DeepFashion In-Shop Clothes Retrieval and CUB200 datasets show that the results of instance retrieval at fine-grained level are promising for these datasets, specially in terms of texture and color.

Space-based missions such as Kepler, and soon TESS, provide large datasets that must be analyzed efficiently and systematically. Recent work by Shallue & Vanderburg (2018) successfully used state-of-the-art deep learning models to automatically classify Kepler transit signals as either exoplanets or false positives; our application of their model yielded 95.8% accuracy and 95.5% average precision. Here we expand upon that work by including additional scientific domain knowledge into the network architecture and input representations to significantly increase overall model performance to 97.5% accuracy and 98.0% average precision. Notably, we achieve 15-20% gains in recall for the lowest signal-to-noise transits that can correspond to rocky planets in the habitable zone. We input into the network centroid time-series information derived from Kepler data plus key stellar parameters taken from the Kepler DR25 catalogue. We also implement data augmentation techniques to alleviate model over-fitting. These improvements allow us to drastically reduce the size of the model, while still maintaining improved performance; smaller models are better for generalization, for example from Kepler to TESS data. This work illustrates the importance of including expert domain knowledge in even state-of-the-art deep learning models when applying them to scientific research problems that seek to identify weak signals in noisy data. This classification tool will be especially useful for upcoming space-based photometry missions focused on finding small planets, such as TESS and PLATO., Comment: 8 pages, 5 figures, accepted to ApJ Letters

DeepFashion is a widely used clothing dataset with 50 categories and more than overall 200k images where each image is annotated with fine-grained attributes. This dataset is often used for clothes recognition and although it provides comprehensive annotations, the attributes distribution is unbalanced and repetitive specially for training fine-grained attribute recognition models. In this work, we tailored DeepFashion for fine-grained attribute recognition task by focusing on each category separately. After selecting categories with sufficient number of images for training, we remove very scarce attributes and merge the duplicate ones in each category, then we clean the dataset based on the new list of attributes. We use a bilinear convolutional neural network with pairwise ranking loss function for multi-label fine-grained attribute recognition and show that the new annotations improve the results for such a task. The detailed annotations for each of the selected categories are provided for public use.

In this paper, we examine the real-time recovery of a video tracker from a target loss, using information that is already available from the original tracker and without a significant computational overhead. More specifically, before using the tracker output to update the target position we estimate the detection confidence. In the case of a low confidence, the position update is rejected and the tracker passes to a single-frame failure mode, during which the patch low-level visual content is used to swiftly update the object position, before recovering from the target loss in the next frame. Orthogonally to this improvement, we further enhance the running average method used for creating the query model in tracking-through-similarity. The experimental evidence provided by evaluation on standard tracking datasets (OTB-50, OTB-100 and OTB-2013) validate that target recovery can be successfully achieved without compromising the real-time update of the target position.

In this paper, we address the extraction of the fine-grained attributes of an instance as a `multi-attribute classification' problem. To this end, we propose an end-to-end architecture by adopting the bi-linear Convolutional Neural Network with the pairwise ranking loss. This is the first time such architecture is applied for the fine-grained attributes classification problem. We compared the proposed method with a competitive deep Convolutional Neural Network baseline. Extensive experiments show that the proposed method attains/outperforms the performance of compared baseline with significantly less number of parameters ($40\times$ less). We demonstrated our approach on CUB200 birds dataset whose annotations are adapted in this work for multi-attribute classification at fine-grained level.

In this paper we detail Cortexica's (https://www.cortexica.com) recommendation framework -- particularly, we describe how a hybrid visual recommender system can be created by combining conditional random fields for segmentation and deep neural networks for object localisation and feature representation. The recommendation system that is built after localisation, segmentation and classification has two properties -- first, it is knowledge based in the sense that it learns pairwise preference/occurrence matrix by utilising knowledge from experts (images from fashion blogs) and second, it is content-based as it utilises a deep learning based framework for learning feature representation. Such a construct is especially useful when there is a scarcity of user preference data, that forms the foundation of many collaborative recommendation algorithms., Comment: KDD 2017 Workshop on ML meets Fashion

With the advent of specialized hardware such as Graphics Processing Units (GPUs), large scale image localization, classification and retrieval have seen increased prevalence. Designing scalable software architecture that co-evolves with such specialized hardware is a challenge in the commercial setting. In this paper, we describe one such architecture (\textit{Cortexica}) that leverages scalability of GPUs and sandboxing offered by docker containers. This allows for the flexibility of mixing different computer architectures as well as computational algorithms with the security of a trusted environment. We illustrate the utility of this framework in a commercial setting i.e., searching for multiple products in an image by combining image localisation and retrieval.