Search

Aligning machine representations with human understanding is key to improving interpretability of machine learning (ML) models. When classifying a new image, humans often explain their decisions by decomposing the image into concepts and pointing to corresponding regions in familiar images. Current ML explanation techniques typically either trace decision-making processes to reference prototypes, generate attribution maps highlighting feature importance, or incorporate intermediate bottlenecks designed to align with human-interpretable concepts. The proposed method, named COMIX, classifies an image by decomposing it into regions based on learned concepts and tracing each region to corresponding ones in images from the training dataset, assuring that explanations fully represent the actual decision-making process. We dissect the test image into selected internal representations of a neural network to derive prototypical parts (primitives) and match them with the corresponding primitives derived from the training data. In a series of qualitative and quantitative experiments, we theoretically prove and demonstrate that our method, in contrast to post hoc analysis, provides fidelity of explanations and shows that the efficiency is competitive with other inherently interpretable architectures. Notably, it shows substantial improvements in fidelity and sparsity metrics, including 48.82% improvement in the C-insertion score on the ImageNet dataset over the best state-of-the-art baseline.

In this paper, we present a novel diffusion model-based monaural speech enhancement method. Our approach incorporates the separate estimation of speech spectra's magnitude and phase in two diffusion networks. Throughout the diffusion process, noise clips from real-world noise interferences are added gradually to the clean speech spectra and a noise-aware reverse process is proposed to learn how to generate both clean speech spectra and noise spectra. Furthermore, to fully leverage the intrinsic relationship between magnitude and phase, we introduce a complex-cycle-consistent (CCC) mechanism that uses the estimated magnitude to map the phase, and vice versa. We implement this algorithm within a phase-aware speech enhancement diffusion model (SEDM). We conduct extensive experiments on public datasets to demonstrate the effectiveness of our method, highlighting the significant benefits of exploiting the intrinsic relationship between phase and magnitude information to enhance speech. The comparison to conventional diffusion models demonstrates the superiority of SEDM., Comment: AAAI 2025

Experimentally measured characteristics of a kHz laser-driven Cu plasma X-ray source that was recently commissioned at ELI Beamlines facility are reported. The source can be driven either by an in-house developed high contrast sub-20 fs near-infrared TW laser based on optical parametric chirped-pulse amplification technology, or by a more conventional Ti:sapphire laser delivering 12 mJ, 45 fs pulses. The X-ray source parameters obtained with the two driving lasers are compared. Measured photon flux of the order up to 10^{12} K{\alpha} photons/4{\pi}/s is reported. Furthermore, experimental platforms for ultrafast X-ray diffraction and X-ray absorption and/or emission spectroscopy based on the reported source are described.

Ptychography is a robust lensless form of microscopy routinely used for applications spanning life and physical sciences. The most common ptychography setup consists in using a detector to record diffraction patterns in the far-field. A near-field version has been more recently introduced, and its potential is yet to be fully exploited. In this work, the sampling requirements for near-field ptychography are analysed. Starting from the characterisation available in literature, the formalism of the fractional Fourier transform is used to generalise analytically the sampling conditions. The results harmonise the far- and near-field regimes and widen the applications of the technique with respect to the current knowledge. This study is supported by simulations and provides clear guidelines on how to optimise the setup and acquisition strategies for near-field ptychography experiments. The results are key to drive the translation of the technique towards low brilliance sources.

We present a novel method to construct particle accelerators targeting light atoms and nuclei using high-power femtosecond laser pulses. Initially, we confine light atoms within the laser pulse envelope due to longitudinal polarization forces, allowing them to acquire kinetic energies of several GeV. Subsequently, an external electric field separates the nuclei at the cathode, concentrating helium nuclei in a small area. The kinetic energy of the 1.88 GeV impacts, exceeding the alpha particle binding energy (28 MeV) by two orders of magnitude, induces powerful gamma radiation and neutron emission from decay processes. This experiment marks a demonstration of a laser-induced decay method for helium nuclei for the first time. Moreover, helium isotopes or deuterium nuclei trapped on the cathode show significantly reduced Coulomb repulsion, enabling subsequent nuclear fusion reactions and substantial nuclear energy release., Comment: Presented at Conference on Advanced Topics in Photonics, CATP 2024, 15-17 July, Sofia Bulgaria

Supervised learning-based adversarial attack detection methods rely on a large number of labeled data and suffer significant performance degradation when applying the trained model to new domains. In this paper, we propose a self-supervised representation learning framework for the adversarial attack detection task to address this drawback. Firstly, we map the pixels of augmented input images into an embedding space. Then, we employ the prototype-wise contrastive estimation loss to cluster prototypes as latent variables. Additionally, drawing inspiration from the concept of memory banks, we introduce a discrimination bank to distinguish and learn representations for each individual instance that shares the same or a similar prototype, establishing a connection between instances and their associated prototypes. We propose a parallel axial-attention (PAA)-based encoder to facilitate the training process by parallel training over height- and width-axis of attention maps. Experimental results show that, compared to various benchmark self-supervised vision learning models and supervised adversarial attack detection methods, the proposed model achieves state-of-the-art performance on the adversarial attack detection task across a wide range of images., Comment: ECCV 2024

As the use of Deep Neural Networks (DNNs) becomes pervasive, their vulnerability to adversarial attacks and limitations in handling unseen classes poses significant challenges. The state-of-the-art offers discrete solutions aimed to tackle individual issues covering specific adversarial attack scenarios, classification or evolving learning. However, real-world systems need to be able to detect and recover from a wide range of adversarial attacks without sacrificing classification accuracy and to flexibly act in {\bf unseen} scenarios. In this paper, UNICAD, is proposed as a novel framework that integrates a variety of techniques to provide an adaptive solution. For the targeted image classification, UNICAD achieves accurate image classification, detects unseen classes, and recovers from adversarial attacks using Prototype and Similarity-based DNNs with denoising autoencoders. Our experiments performed on the CIFAR-10 dataset highlight UNICAD's effectiveness in adversarial mitigation and unseen class classification, outperforming traditional models.

As the development of deep learning techniques in autonomous landing systems continues to grow, one of the major challenges is trust and security in the face of possible adversarial attacks. In this paper, we propose a federated adversarial learning-based framework to detect landing runways using paired data comprising of clean local data and its adversarial version. Firstly, the local model is pre-trained on a large-scale lane detection dataset. Then, instead of exploiting large instance-adaptive models, we resort to a parameter-efficient fine-tuning method known as scale and shift deep features (SSF), upon the pre-trained model. Secondly, in each SSF layer, distributions of clean local data and its adversarial version are disentangled for accurate statistics estimation. To the best of our knowledge, this marks the first instance of federated learning work that address the adversarial sample problem in landing runway detection. Our experimental evaluations over both synthesis and real images of Landing Approach Runway Detection (LARD) dataset consistently demonstrate good performance of the proposed federated adversarial learning and robust to adversarial attacks., Comment: ICANN2024

Deepfake techniques generate highly realistic data, making it challenging for humans to discern between actual and artificially generated images. Recent advancements in deep learning-based deepfake detection methods, particularly with diffusion models, have shown remarkable progress. However, there is a growing demand for real-world applications to detect unseen individuals, deepfake techniques, and scenarios. To address this limitation, we propose a Prototype-based Unified Framework for Deepfake Detection (PUDD). PUDD offers a detection system based on similarity, comparing input data against known prototypes for video classification and identifying potential deepfakes or previously unseen classes by analyzing drops in similarity. Our extensive experiments reveal three key findings: (1) PUDD achieves an accuracy of 95.1% on Celeb-DF, outperforming state-of-the-art deepfake detection methods; (2) PUDD leverages image classification as the upstream task during training, demonstrating promising performance in both image classification and deepfake detection tasks during inference; (3) PUDD requires only 2.7 seconds for retraining on new data and emits 10$^{5}$ times less carbon compared to the state-of-the-art model, making it significantly more environmentally friendly., Comment: CVPR2024

In this paper, we address two critical challenges in the domain of flood detection: the computational expense of large-scale time series change detection and the lack of interpretable decision-making processes on explainable AI (XAI). To overcome these challenges, we proposed an interpretable multi-stage approach to flood detection, IMAFD has been proposed. It provides an automatic, efficient and interpretable solution suitable for large-scale remote sensing tasks and offers insight into the decision-making process. The proposed IMAFD approach combines the analysis of the dynamic time series image sequences to identify images with possible flooding with the static, within-image semantic segmentation. It combines anomaly detection (at both image and pixel level) with semantic segmentation. The flood detection problem is addressed through four stages: (1) at a sequence level: identifying the suspected images (2) at a multi-image level: detecting change within suspected images (3) at an image level: semantic segmentation of images into Land, Water or Cloud class (4) decision making. Our contributions are two folder. First, we efficiently reduced the number of frames to be processed for dense change detection by providing a multi-stage holistic approach to flood detection. Second, the proposed semantic change detection method (stage 3) provides human users with an interpretable decision-making process, while most of the explainable AI (XAI) methods provide post hoc explanations. The evaluation of the proposed IMAFD framework was performed on three datasets, WorldFloods, RavAEn and MediaEval. For all the above datasets, the proposed framework demonstrates a competitive performance compared to other methods offering also interpretability and insight.

The vision transformer-based foundation models, such as ViT or Dino-V2, are aimed at solving problems with little or no finetuning of features. Using a setting of prototypical networks, we analyse to what extent such foundation models can solve unsupervised domain adaptation without finetuning over the source or target domain. Through quantitative analysis, as well as qualitative interpretations of decision making, we demonstrate that the suggested method can improve upon existing baselines, as well as showcase the limitations of such approach yet to be solved.

The proposed framework named IDEAL (Interpretable-by-design DEep learning ALgorithms) recasts the standard supervised classification problem into a function of similarity to a set of prototypes derived from the training data, while taking advantage of existing latent spaces of large neural networks forming so-called Foundation Models (FM). This addresses the issue of explainability (stage B) while retaining the benefits from the tremendous achievements offered by DL models (e.g., visual transformers, ViT) pre-trained on huge data sets such as IG-3.6B + ImageNet-1K or LVD-142M (stage A). We show that one can turn such DL models into conceptually simpler, explainable-through-prototypes ones. The key findings can be summarized as follows: (1) the proposed models are interpretable through prototypes, mitigating the issue of confounded interpretations, (2) the proposed IDEAL framework circumvents the issue of catastrophic forgetting allowing efficient class-incremental learning, and (3) the proposed IDEAL approach demonstrates that ViT architectures narrow the gap between finetuned and non-finetuned models allowing for transfer learning in a fraction of time \textbf{without} finetuning of the feature space on a target dataset with iterative supervised methods.

Demand Side Response (DSR) is a strategy that enables consumers to actively participate in managing electricity demand. It aims to alleviate strain on the grid during high demand and promote a more balanced and efficient use of (renewable) electricity resources. We implement DSR through discount scheduling, which involves offering discrete price incentives to consumers to adjust their electricity consumption patterns to times when their local energy mix consists of more renewable energy. Since we tailor the discounts to individual customers' consumption, the Discount Scheduling Problem (DSP) becomes a large combinatorial optimization task. Consequently, we adopt a hybrid quantum computing approach, using D-Wave's Leap Hybrid Cloud. We benchmark Leap against Gurobi, a classical Mixed Integer optimizer in terms of solution quality at fixed runtime and fairness in terms of discount allocation. Furthermore, we propose a large-scale decomposition algorithm/heuristic for the DSP, applied with either quantum or classical computers running the subroutines, which significantly reduces the problem size while maintaining solution quality. Using synthetic data generated from real-world data, we observe that the classical decomposition method obtains the best overall \newp{solution quality for problem sizes up to 3200 consumers, however, the hybrid quantum approach provides more evenly distributed discounts across consumers.

On November 3-4 2021, an interplanetary coronal mass injection (ICME) hits the magnetosphere, sparking a strong G3-class geomagnetic storm and auroras as far south as California and New Mexico. All detectors of the SEVAN network registered a Forbush decrease (FD) of 5-10 percentdeep in 1 minute time series of count rates. We present the results of a comparison of Fd registered on mountain altitudes on Aragats (Armenia), Lomnicky Stit (Slovakia), Musala (Bulgaria), and at sea level DESY (Hamburg, Germany), and in Mileshovka, Czechia. We present as well purity and barometric coefficients of different coincidences of SEVAN detector layers on Aragats. We demonstrate disturbances of the near-surface electric (NSEF) and geomagnetic fields at the arrival of the ICME on Earth.

Earth observation is fundamental for a range of human activities including flood response as it offers vital information to decision makers. Semantic segmentation plays a key role in mapping the raw hyper-spectral data coming from the satellites into a human understandable form assigning class labels to each pixel. In this paper, we introduce a prototype-based interpretable deep semantic segmentation (IDSS) method, which is highly accurate as well as interpretable. Its parameters are in orders of magnitude less than the number of parameters used by deep networks such as U-Net and are clearly interpretable by humans. The proposed here IDSS offers a transparent structure that allows users to inspect and audit the algorithm's decision. Results have demonstrated that IDSS could surpass other algorithms, including U-Net, in terms of IoU (Intersection over Union) total water and Recall total water. We used WorldFloods data set for our experiments and plan to use the semantic segmentation results combined with masks for permanent water to detect flood events.

In this paper, we propose a novel hand-based person recognition method for the purpose of criminal investigations since the hand image is often the only available information in cases of serious crime such as sexual abuse. Our proposed method, Multi-Branch with Attention Network (MBA-Net), incorporates both channel and spatial attention modules in branches in addition to a global (without attention) branch to capture global structural information for discriminative feature learning. The attention modules focus on the relevant features of the hand image while suppressing the irrelevant backgrounds. In order to overcome the weakness of the attention mechanisms, equivariant to pixel shuffling, we integrate relative positional encodings into the spatial attention module to capture the spatial positions of pixels. Extensive evaluations on two large multi-ethnic and publicly available hand datasets demonstrate that our proposed method achieves state-of-the-art performance, surpassing the existing hand-based identification methods., Comment: arXiv admin note: text overlap with arXiv:2101.05260

In cases of serious crime, including sexual abuse, often the only available information with demonstrated potential for identification is images of the hands. Since this evidence is captured in uncontrolled situations, it is difficult to analyse. As global approaches to feature comparison are limited in this case, it is important to extend to consider local information. In this work, we propose hand-based person identification by learning both global and local deep feature representations. Our proposed method, Global and Part-Aware Network (GPA-Net), creates global and local branches on the conv-layer for learning robust discriminative global and part-level features. For learning the local (part-level) features, we perform uniform partitioning on the conv-layer in both horizontal and vertical directions. We retrieve the parts by conducting a soft partition without explicitly partitioning the images or requiring external cues such as pose estimation. We make extensive evaluations on two large multi-ethnic and publicly available hand datasets, demonstrating that our proposed method significantly outperforms competing approaches.

The pandemic caused by Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) has affected countries all across the world, heavily burdening the medical infrastructure with the growing number of patients affected by the coronavirus disease (COVID-19). With ventilators in limited supply, this public health emergency highlights the need for safe, fast, reliable, and economical alternatives to high-end commercial devices and has prompted the development of easy-to-use and mass-producible ventilators. Here, we detail the design of the HDvent Emergency Ventilator System. The device performs ventilation through mechanical compression of manual resuscitators and includes control electronics, flow and pressure sensors, and an external data visualization and monitoring unit. We demonstrate its suitability for open loop, pressure- and volume-controlled ventilation. The system has not undergone clinical testing and has not been approved for use as a medical device. The project documentation needed to reproduce the prototype is freely available and will contribute to the development of open source ventilation systems., Comment: All source files available at https://github.com/HDventilator/

Global climate change has had a drastic impact on our environment. Previous study showed that pest disaster occured from global climate change may cause a tremendous number of trees died and they inevitably became a factor of forest fire. An important portent of the forest fire is the condition of forests. Aerial image-based forest analysis can give an early detection of dead trees and living trees. In this paper, we applied a synthetic method to enlarge imagery dataset and present a new framework for automated dead tree detection from aerial images using a re-trained Mask RCNN (Mask Region-based Convolutional Neural Network) approach, with a transfer learning scheme. We apply our framework to our aerial imagery datasets,and compare eight fine-tuned models. The mean average precision score (mAP) for the best of these models reaches 54%. Following the automated detection, we are able to automatically produce and calculate number of dead tree masks to label the dead trees in an image, as an indicator of forest health that could be linked to the causal analysis of environmental changes and the predictive likelihood of forest fire., Comment: 16 pages

Topic modeling is used for discovering latent semantic structure, usually referred to as topics, in a large collection of documents. The most widely used methods are Latent Dirichlet Allocation and Probabilistic Latent Semantic Analysis. Despite their popularity they have several weaknesses. In order to achieve optimal results they often require the number of topics to be known, custom stop-word lists, stemming, and lemmatization. Additionally these methods rely on bag-of-words representation of documents which ignore the ordering and semantics of words. Distributed representations of documents and words have gained popularity due to their ability to capture semantics of words and documents. We present $\texttt{top2vec}$, which leverages joint document and word semantic embedding to find $\textit{topic vectors}$. This model does not require stop-word lists, stemming or lemmatization, and it automatically finds the number of topics. The resulting topic vectors are jointly embedded with the document and word vectors with distance between them representing semantic similarity. Our experiments demonstrate that $\texttt{top2vec}$ finds topics which are significantly more informative and representative of the corpus trained on than probabilistic generative models., Comment: Implementation available at https://github.com/ddangelov/Top2Vec

Learning models of user behaviour is an important problem that is broadly applicable across many application domains requiring human-robot interaction. In this work, we show that it is possible to learn generative models for distinct user behavioural types, extracted from human demonstrations, by enforcing clustering of preferred task solutions within the latent space. We use these models to differentiate between user types and to find cases with overlapping solutions. Moreover, we can alter an initially guessed solution to satisfy the preferences that constitute a particular user type by backpropagating through the learned differentiable models. An advantage of structuring generative models in this way is that we can extract causal relationships between symbols that might form part of the user's specification of the task, as manifested in the demonstrations. We further parameterize these specifications through constraint optimization in order to find a safety envelope under which motion planning can be performed. We show that the proposed method is capable of correctly distinguishing between three user types, who differ in degrees of cautiousness in their motion, while performing the task of moving objects with a kinesthetically driven robot in a tabletop environment. Our method successfully identifies the correct type, within the specified time, in 99% [97.8 - 99.8] of the cases, which outperforms an IRL baseline. We also show that our proposed method correctly changes a default trajectory to one satisfying a particular user specification even with unseen objects. The resulting trajectory is shown to be directly implementable on a PR2 humanoid robot completing the same task., Comment: arXiv admin note: substantial text overlap with arXiv:1903.01267

Informative path-planning is a well established approach to visual-servoing and active viewpoint selection in robotics, but typically assumes that a suitable cost function or goal state is known. This work considers the inverse problem, where the goal of the task is unknown, and a reward function needs to be inferred from exploratory example demonstrations provided by a demonstrator, for use in a downstream informative path-planning policy. Unfortunately, many existing reward inference strategies are unsuited to this class of problems, due to the exploratory nature of the demonstrations. In this paper, we propose an alternative approach to cope with the class of problems where these sub-optimal, exploratory demonstrations occur. We hypothesise that, in tasks which require discovery, successive states of any demonstration are progressively more likely to be associated with a higher reward, and use this hypothesis to generate time-based binary comparison outcomes and infer reward functions that support these ranks, under a probabilistic generative model. We formalise this \emph{probabilistic temporal ranking} approach and show that it improves upon existing approaches to perform reward inference for autonomous ultrasound scanning, a novel application of learning from demonstration in medical imaging while also being of value across a broad range of goal-oriented learning from demonstration tasks. \keywords{Visual servoing \and reward inference \and probabilistic temporal ranking, Comment: Accepted for publication at Springer Autonomous Robots, 2023

In this paper we introduce the DMR -- a prototype-based method and network architecture for deep learning which is using a decision tree (DT)-based inference and synthetic data to balance the classes. It builds upon the recently introduced xDNN method addressing more complex multi-class problems, specifically when classes are highly imbalanced. DMR moves away from a direct decision based on all classes towards a layered DT of pair-wise class comparisons. In addition, it forces the prototypes to be balanced between classes regardless of possible class imbalances of the training data. It has two novel mechanisms, namely i) using a DT to determine the winning class label, and ii) balancing the classes by synthesizing data around the prototypes determined from the available training data. As a result, we improved significantly the performance of the resulting fully explainable DNN as evidenced by the best reported result on the well know benchmark problem Caltech-101 surpassing our own recently published "world record". Furthermore, we also achieved another "world record" for another very hard benchmark problem, namely Caltech-256 as well as surpassed the results of other approaches on Faces-1999 problem. In summary, we propose a new approach specifically advantageous for imbalanced multi-class problems that achieved two world records on well known hard benchmark problems and the best result on another problem in terms of accuracy. Moreover, DMR offers full explainability, does not require GPUs and can continue to learn from new data by adding new prototypes preserving the previous ones but not requiring full retraining., Comment: Submitted to the IEEE Joint Conference on Neural Networks (IJCNN - 2020)