Dario Zanca

Leo Schwinn, Leon Bungert, An Nguyen et al.

The reliability of neural networks is essential for their use in safety-critical applications. Existing approaches generally aim at improving the robustness of neural networks to either real-world distribution shifts (e.g., common corruptions and perturbations, spatial transformations, and natural adversarial examples) or worst-case distribution shifts (e.g., optimized adversarial examples). In this work, we propose the Decision Region Quantification (DRQ) algorithm to improve the robustness of any differentiable pre-trained model against both real-world and worst-case distribution shifts in the data. DRQ analyzes the robustness of local decision regions in the vicinity of a given data point to make more reliable predictions. We theoretically motivate the DRQ algorithm by showing that it effectively smooths spurious local extrema in the decision surface. Furthermore, we propose an implementation using targeted and untargeted adversarial attacks. An extensive empirical evaluation shows that DRQ increases the robustness of adversarially and non-adversarially trained models against real-world and worst-case distribution shifts on several computer vision benchmark datasets.

Sami Ede, Serop Baghdadlian, Leander Weber et al.

The ability to continuously process and retain new information like we do naturally as humans is a feat that is highly sought after when training neural networks. Unfortunately, the traditional optimization algorithms often require large amounts of data available during training time and updates wrt. new data are difficult after the training process has been completed. In fact, when new data or tasks arise, previous progress may be lost as neural networks are prone to catastrophic forgetting. Catastrophic forgetting describes the phenomenon when a neural network completely forgets previous knowledge when given new information. We propose a novel training algorithm called training by explaining in which we leverage Layer-wise Relevance Propagation in order to retain the information a neural network has already learned in previous tasks when training on new data. The method is evaluated on a range of benchmark datasets as well as more complex data. Our method not only successfully retains the knowledge of old tasks within the neural networks but does so more resource-efficiently than other state-of-the-art solutions.

Leo Schwinn, Doina Precup, Björn Eskofier et al.

By and large, existing computational models of visual attention tacitly assume perfect vision and full access to the stimulus and thereby deviate from foveated biological vision. Moreover, modeling top-down attention is generally reduced to the integration of semantic features without incorporating the signal of a high-level visual tasks that have been shown to partially guide human attention. We propose the Neural Visual Attention (NeVA) algorithm to generate visual scanpaths in a top-down manner. With our method, we explore the ability of neural networks on which we impose a biologically-inspired foveated vision constraint to generate human-like scanpaths without directly training for this objective. The loss of a neural network performing a downstream visual task (i.e., classification or reconstruction) flexibly provides top-down guidance to the scanpath. Extensive experiments show that our method outperforms state-of-the-art unsupervised human attention models in terms of similarity to human scanpaths. Additionally, the flexibility of the framework allows to quantitatively investigate the role of different tasks in the generated visual behaviors. Finally, we demonstrate the superiority of the approach in a novel experiment that investigates the utility of scanpaths in real-world applications, where imperfect viewing conditions are given.

Leo Schwinn, Doina Precup, Bjoern Eskofier et al.

Existing models of human visual attention are generally unable to incorporate direct task guidance and therefore cannot model an intent or goal when exploring a scene. To integrate guidance of any downstream visual task into attention modeling, we propose the Neural Visual Attention (NeVA) algorithm. To this end, we impose to neural networks the biological constraint of foveated vision and train an attention mechanism to generate visual explorations that maximize the performance with respect to the downstream task. We observe that biologically constrained neural networks generate human-like scanpaths without being trained for this objective. Extensive experiments on three common benchmark datasets show that our method outperforms state-of-the-art unsupervised human attention models in generating human-like scanpaths.

Christoffer Loeffler, Kion Fallah, Stefano Fenu et al.

Humans innately measure distance between instances in an unlabeled dataset using an unknown similarity function. Distance metrics can only serve as proxy for similarity in information retrieval of similar instances. Learning a good similarity function from human annotations improves the quality of retrievals. This work uses deep metric learning to learn these user-defined similarity functions from few annotations for a large football trajectory dataset. We adapt an entropy-based active learning method with recent work from triplet mining to collect easy-to-answer but still informative annotations from human participants and use them to train a deep convolutional network that generalizes to unseen samples. Our user study shows that our approach improves the quality of the information retrieval compared to a previous deep metric learning approach that relies on a Siamese network. Specifically, we shed light on the strengths and weaknesses of passive sampling heuristics and active learners alike by analyzing the participants' response efficacy. To this end, we collect accuracy, algorithmic time complexity, the participants' fatigue and time-to-response, qualitative self-assessment and statements, as well as the effects of mixed-expertise annotators and their consistency on model performance and transfer-learning.

Christoffer Loeffler, Wei-Cheng Lai, Bjoern Eskofier et al.

The correct interpretation of convolutional models is a hard problem for time series data. While saliency methods promise visual validation of predictions for image and language processing, they fall short when applied to time series. These tend to be less intuitive and represent highly diverse data, such as the tool-use time series dataset. Furthermore, saliency methods often generate varied, conflicting explanations, complicating the reliability of these methods. Consequently, a rigorous objective assessment is necessary to establish trust in them. This paper investigates saliency methods on time series data to formulate recommendations for interpreting convolutional models and implements them on the tool-use time series problem. To achieve this, we first employ nine gradient-, propagation-, or perturbation-based post-hoc saliency methods across six varied and complex real-world datasets. Next, we evaluate these methods using five independent metrics to generate recommendations. Subsequently, we implement a case study focusing on tool-use time series using convolutional classification models. Our results validate our recommendations that indicate that none of the saliency methods consistently outperforms others on all metrics, while some are sometimes ahead. Our insights and step-by-step guidelines allow experts to choose suitable saliency methods for a given model and dataset.

Thomas Altstidl, An Nguyen, Leo Schwinn et al.

The widespread success of convolutional neural networks may largely be attributed to their intrinsic property of translation equivariance. However, convolutions are not equivariant to variations in scale and fail to generalize to objects of different sizes. Despite recent advances in this field, it remains unclear how well current methods generalize to unobserved scales on real-world data and to what extent scale equivariance plays a role. To address this, we propose the novel Scaled and Translated Image Recognition (STIR) benchmark based on four different domains. Additionally, we introduce a new family of models that applies many re-scaled kernels with shared weights in parallel and then selects the most appropriate one. Our experimental results on STIR show that both the existing and proposed approaches can improve generalization across scales compared to standard convolutions. We also demonstrate that our family of models is able to generalize well towards larger scales and improve scale equivariance. Moreover, due to their unique design we can validate that kernel selection is consistent with input scale. Even so, none of the evaluated models maintain their performance for large differences in scale, demonstrating that a general understanding of how scale equivariance can improve generalization and robustness is still lacking.

Mahadev Prasad Panda, Matteo Tiezzi, Martina Vilas et al.

Explainability in artificial intelligence (XAI) remains a crucial aspect for fostering trust and understanding in machine learning models. Current visual explanation techniques, such as gradient-based or class-activation-based methods, often exhibit a strong dependence on specific model architectures. Conversely, perturbation-based methods, despite being model-agnostic, are computationally expensive as they require evaluating models on a large number of forward passes. In this work, we introduce Foveation-based Explanations (FovEx), a novel XAI method inspired by human vision. FovEx seamlessly integrates biologically inspired perturbations by iteratively creating foveated renderings of the image and combines them with gradient-based visual explorations to determine locations of interest efficiently. These locations are selected to maximize the performance of the model to be explained with respect to the downstream task and then combined to generate an attribution map. We provide a thorough evaluation with qualitative and quantitative assessments on established benchmarks. Our method achieves state-of-the-art performance on both transformers (on 4 out of 5 metrics) and convolutional models (on 3 out of 5 metrics), demonstrating its versatility among various architectures. Furthermore, we show the alignment between the explanation map produced by FovEx and human gaze patterns (+14\% in NSS compared to RISE, +203\% in NSS compared to GradCAM). This comparison enhances our confidence in FovEx's ability to close the interpretation gap between humans and machines.

Giuseppe Cartella, Marcella Cornia, Vittorio Cuculo et al.

Human attention modelling has proven, in recent years, to be particularly useful not only for understanding the cognitive processes underlying visual exploration, but also for providing support to artificial intelligence models that aim to solve problems in various domains, including image and video processing, vision-and-language applications, and language modelling. This survey offers a reasoned overview of recent efforts to integrate human attention mechanisms into contemporary deep learning models and discusses future research directions and challenges. For a comprehensive overview on the ongoing research refer to our dedicated repository available at https://github.com/aimagelab/awesome-human-visual-attention.

Dario Zanca, Andrea Zugarini, Simon Dietz et al.

Understanding human attention is crucial for vision science and AI. While many models exist for free-viewing, less is known about task-driven image exploration. To address this, we introduce CapMIT1003, a dataset with captions and click-contingent image explorations, to study human attention during the captioning task. We also present NevaClip, a zero-shot method for predicting visual scanpaths by combining CLIP models with NeVA algorithms. NevaClip generates fixations to align the representations of foveated visual stimuli and captions. The simulated scanpaths outperform existing human attention models in plausibility for captioning and free-viewing tasks. This research enhances the understanding of human attention and advances scanpath prediction models.

Jindong Li, Dario Zanca, Vincent Christlein et al.

Inertial measurement unit-based online handwriting recognition enables the recognition of input signals collected across different writing surfaces but remains challenged by uneven character distributions and inter-writer variability. In this work, we systematically investigate two strategies to address these issues: sub-word tokenization and concatenation-based data augmentation. Our experiments on the OnHW-Words500 dataset reveal a clear dichotomy between handling inter-writer and intra-writer variance. On the writer-independent split, structural abstraction via Bigram tokenization significantly improves performance to unseen writing styles, reducing the word error rate (WER) from 15.40% to 12.99%. In contrast, on the writer-dependent split, tokenization degrades performance due to vocabulary distribution shifts between the training and validation sets. Instead, our proposed concatenation-based data augmentation acts as a powerful regularizer, reducing the character error rate by 34.5% and the WER by 25.4%. Further analysis shows that short, low-level tokens benefit model performance and that concatenation-based data augmentation performance gain surpasses those achieved by proportionally extended training. These findings reveal a clear variance-dependent effect: sub-word tokenization primarily mitigates inter-writer stylistic variability, whereas concatenation-based data augmentation effectively compensates for intra-writer distributional sparsity.

Naga Venkata Sai Jitin Jami, Thomas Altstidl, Jonas Mueller et al.

Random splitting of datasets in image segmentation often leads to unrepresentative test sets, resulting in biased evaluations and poor model generalization. While stratified sampling has proven effective for addressing label distribution imbalance in classification tasks, extending these ideas to segmentation remains challenging due to the multi-label structure and class imbalance typically present in such data. Building on existing stratification concepts, we introduce Iterative Pixel Stratification (IPS), a straightforward, label-aware sampling method tailored for segmentation tasks. Additionally, we present Wasserstein-Driven Evolutionary Stratification (WDES), a novel genetic algorithm designed to minimize the Wasserstein distance, thereby optimizing the similarity of label distributions across dataset splits. We prove that WDES is globally optimal given enough generations. Using newly proposed statistical heterogeneity metrics, we evaluate both methods against random sampling and find that WDES consistently produces more representative splits. Applying WDES across diverse segmentation tasks, including street scenes, medical imaging, and satellite imagery, leads to lower performance variance and improved model evaluation. Our results also highlight the particular value of WDES in handling small, imbalanced, and low-diversity datasets, where conventional splitting strategies are most prone to bias.

Richard Dirauf, Florian Wolz, Dario Zanca et al.

Content-based puzzle solvers have been extensively studied, demonstrating significant progress in computational techniques. However, their evaluation often lacks realistic challenges crucial for real-world applications, such as the reassembly of fragmented artefacts or shredded documents. In this work, we investigate the robustness of State-Of-The-Art content-based puzzle solvers introducing three types of jigsaw puzzle corruptions: missing pieces, eroded edges, and eroded contents. Evaluating both heuristic and deep learning-based solvers, we analyse their ability to handle these corruptions and identify key limitations. Our results show that solvers developed for standard puzzles have a rapid decline in performance if more pieces are corrupted. However, deep learning models can significantly improve their robustness through fine-tuning with augmented data. Notably, the advanced Positional Diffusion model adapts particularly well, outperforming its competitors in most experiments. Based on our findings, we highlight promising research directions for enhancing the automated reconstruction of real-world artefacts.

Lukas Boehm, Jonas Leo Mueller, Christoffer Loeffler et al.

Understanding the perceptual invariances of artificial neural networks is essential for improving explainability and aligning models with human vision. Metamers - stimuli that are physically distinct yet produce identical neural activations - serve as a valuable tool for investigating these invariances. We introduce a novel approach to metamer generation by leveraging ensembles of artificial neural networks, capturing shared representational subspaces across diverse architectures, including convolutional neural networks and vision transformers. To characterize the properties of the generated metamers, we employ a suite of image-based metrics that assess factors such as semantic fidelity and naturalness. Our findings show that convolutional neural networks generate more recognizable and human-like metamers, while vision transformers produce realistic but less transferable metamers, highlighting the impact of architectural biases on representational invariances.

Jindong Li, Tim Hamann, Jens Barth et al.

Online handwriting recognition (HWR) using data from inertial measurement units (IMUs) remains challenging due to variations in writing styles and the limited availability of annotated datasets. Previous approaches often struggle with handwriting from unseen writers, making writer-independent (WI) recognition a crucial yet difficult problem. This paper presents an HWR model designed to improve WI HWR on IMU data, using a CNN encoder and a BiLSTM-based decoder. Our approach demonstrates strong robustness to unseen handwriting styles, outperforming existing methods on the WI splits of both the public OnHW dataset and our word-based dataset, achieving character error rates (CERs) of 7.37\% and 9.44\%, and word error rates (WERs) of 15.12\% and 32.17\%, respectively. Robustness evaluation shows that our model maintains superior accuracy across different age groups, and knowledge learned from one group generalizes better to another. Evaluation on our sentence-based dataset further demonstrates its potential in recognizing full sentences. Through comprehensive ablation studies, we show that our design choices lead to a strong balance between performance and efficiency. These findings support the development of more adaptable and scalable HWR systems for real-world applications.

Simon Dietz, Thomas Altstidl, Dario Zanca et al.

Mixed-type time series (MTTS) is a bimodal data type that is common in many domains, such as healthcare, finance, environmental monitoring, and social media. It consists of regularly sampled continuous time series and irregularly sampled categorical event sequences. The integration of both modalities through multimodal fusion is a promising approach for processing MTTS. However, the question of how to effectively fuse both modalities remains open. In this paper, we present a comprehensive evaluation of several deep multimodal fusion approaches for MTTS forecasting. Our comparison includes three fusion types (early, intermediate, and late) and five fusion methods (concatenation, weighted mean, weighted mean with correlation, gating, and feature sharing). We evaluate these fusion approaches on three distinct datasets, one of which was generated using a novel framework. This framework allows for the control of key data properties, such as the strength and direction of intermodal interactions, modality imbalance, and the degree of randomness in each modality, providing a more controlled environment for testing fusion approaches. Our findings show that the performance of different fusion approaches can be substantially influenced by the direction and strength of intermodal interactions. The study reveals that early and intermediate fusion approaches excel at capturing fine-grained and coarse-grained cross-modal features, respectively. These findings underscore the crucial role of intermodal interactions in determining the most effective fusion strategy for MTTS forecasting.

Toni Albert, Bjoern Eskofier, Dario Zanca

As the field of deep learning steadily transitions from the realm of academic research to practical application, the significance of self-supervised pretraining methods has become increasingly prominent. These methods, particularly in the image domain, offer a compelling strategy to effectively utilize the abundance of unlabeled image data, thereby enhancing downstream tasks' performance. In this paper, we propose a novel auxiliary pretraining method that is based on spatial reasoning. Our proposed method takes advantage of a more flexible formulation of contrastive learning by introducing spatial reasoning as an auxiliary task for discriminative self-supervised methods. Spatial Reasoning works by having the network predict the relative distances between sampled non-overlapping patches. We argue that this forces the network to learn more detailed and intricate internal representations of the objects and the relationships between their constituting parts. Our experiments demonstrate substantial improvement in downstream performance in linear evaluation compared to similar work and provide directions for further research into spatial reasoning.

Dario Zanca, Andrea Zugarini, Simon Dietz et al.

Understanding the mechanisms underlying human attention is a fundamental challenge for both vision science and artificial intelligence. While numerous computational models of free-viewing have been proposed, less is known about the mechanisms underlying task-driven image exploration. To address this gap, we present CapMIT1003, a database of captions and click-contingent image explorations collected during captioning tasks. CapMIT1003 is based on the same stimuli from the well-known MIT1003 benchmark, for which eye-tracking data under free-viewing conditions is available, which offers a promising opportunity to concurrently study human attention under both tasks. We make this dataset publicly available to facilitate future research in this field. In addition, we introduce NevaClip, a novel zero-shot method for predicting visual scanpaths that combines contrastive language-image pretrained (CLIP) models with biologically-inspired neural visual attention (NeVA) algorithms. NevaClip simulates human scanpaths by aligning the representation of the foveated visual stimulus and the representation of the associated caption, employing gradient-driven visual exploration to generate scanpaths. Our experimental results demonstrate that NevaClip outperforms existing unsupervised computational models of human visual attention in terms of scanpath plausibility, for both captioning and free-viewing tasks. Furthermore, we show that conditioning NevaClip with incorrect or misleading captions leads to random behavior, highlighting the significant impact of caption guidance in the decision-making process. These findings contribute to a better understanding of mechanisms that guide human attention and pave the way for more sophisticated computational approaches to scanpath prediction that can integrate direct top-down guidance of downstream tasks.

Kai Klede, Leo Schwinn, Dario Zanca et al.

Clustering is at the very core of machine learning, and its applications proliferate with the increasing availability of data. However, as datasets grow, comparing clusterings with an adjustment for chance becomes computationally difficult, preventing unbiased ground-truth comparisons and solution selection. We propose FastAMI, a Monte Carlo-based method to efficiently approximate the Adjusted Mutual Information (AMI) and extend it to the Standardized Mutual Information (SMI). The approach is compared with the exact calculation and a recently developed variant of the AMI based on pairwise permutations, using both synthetic and real data. In contrast to the exact calculation our method is fast enough to enable these adjusted information-theoretic comparisons for large datasets while maintaining considerably more accurate results than the pairwise approach.

Ruben Tolosana, Ruben Vera-Rodriguez, Carlos Gonzalez-Garcia et al.

This article presents SVC-onGoing, an on-going competition for on-line signature verification where researchers can easily benchmark their systems against the state of the art in an open common platform using large-scale public databases, such as DeepSignDB and SVC2021_EvalDB, and standard experimental protocols. SVC-onGoing is based on the ICDAR 2021 Competition on On-Line Signature Verification (SVC 2021), which has been extended to allow participants anytime. The goal of SVC-onGoing is to evaluate the limits of on-line signature verification systems on popular scenarios (office/mobile) and writing inputs (stylus/finger) through large-scale public databases. Three different tasks are considered in the competition, simulating realistic scenarios as both random and skilled forgeries are simultaneously considered on each task. The results obtained in SVC-onGoing prove the high potential of deep learning methods in comparison with traditional methods. In particular, the best signature verification system has obtained Equal Error Rate (EER) values of 3.33% (Task 1), 7.41% (Task 2), and 6.04% (Task 3). Future studies in the field should be oriented to improve the performance of signature verification systems on the challenging mobile scenarios of SVC-onGoing in which several mobile devices and the finger are used during the signature acquisition.

Ruben Tolosana, Ruben Vera-Rodriguez, Carlos Gonzalez-Garcia et al.

This paper describes the experimental framework and results of the ICDAR 2021 Competition on On-Line Signature Verification (SVC 2021). The goal of SVC 2021 is to evaluate the limits of on-line signature verification systems on popular scenarios (office/mobile) and writing inputs (stylus/finger) through large-scale public databases. Three different tasks are considered in the competition, simulating realistic scenarios as both random and skilled forgeries are simultaneously considered on each task. The results obtained in SVC 2021 prove the high potential of deep learning methods. In particular, the best on-line signature verification system of SVC 2021 obtained Equal Error Rate (EER) values of 3.33% (Task 1), 7.41% (Task 2), and 6.04% (Task 3). SVC 2021 will be established as an on-going competition, where researchers can easily benchmark their systems against the state of the art in an open common platform using large-scale public databases such as DeepSignDB and SVC2021_EvalDB, and standard experimental protocols.

Mohamad Wehbi, Tim Hamann, Jens Barth et al.

Most online handwriting recognition systems require the use of specific writing surfaces to extract positional data. In this paper we present a online handwriting recognition system for word recognition which is based on inertial measurement units (IMUs) for digitizing text written on paper. This is obtained by means of a sensor-equipped pen that provides acceleration, angular velocity, and magnetic forces streamed via Bluetooth. Our model combines convolutional and bidirectional LSTM networks, and is trained with the Connectionist Temporal Classification loss that allows the interpretation of raw sensor data into words without the need of sequence segmentation. We use a dataset of words collected using multiple sensor-enhanced pens and evaluate our model on distinct test sets of seen and unseen words achieving a character error rate of 17.97% and 17.08%, respectively, without the use of a dictionary or language model

Leo Schwinn, René Raab, An Nguyen et al.

Progress in making neural networks more robust against adversarial attacks is mostly marginal, despite the great efforts of the research community. Moreover, the robustness evaluation is often imprecise, making it difficult to identify promising approaches. We analyze the classification decisions of 19 different state-of-the-art neural networks trained to be robust against adversarial attacks. Our findings suggest that current untargeted adversarial attacks induce misclassification towards only a limited amount of different classes. Additionally, we observe that both over- and under-confidence in model predictions result in an inaccurate assessment of model robustness. Based on these observations, we propose a novel loss function for adversarial attacks that consistently improves attack success rate compared to prior loss functions for 19 out of 19 analyzed models.

Leo Schwinn, An Nguyen, René Raab et al.

The susceptibility of deep neural networks to untrustworthy predictions, including out-of-distribution (OOD) data and adversarial examples, still prevent their widespread use in safety-critical applications. Most existing methods either require a re-training of a given model to achieve robust identification of adversarial attacks or are limited to out-of-distribution sample detection only. In this work, we propose a geometric gradient analysis (GGA) to improve the identification of untrustworthy predictions without retraining of a given model. GGA analyzes the geometry of the loss landscape of neural networks based on the saliency maps of their respective input. To motivate the proposed approach, we provide theoretical connections between gradients' geometrical properties and local minima of the loss function. Furthermore, we demonstrate that the proposed method outperforms prior approaches in detecting OOD data and adversarial attacks, including state-of-the-art and adaptive attacks.

An Nguyen, Stefan Foerstel, Thomas Kittler et al.

The most important goal of customer services is to keep the customer satisfied. However, service resources are always limited and must be prioritized. Therefore, it is important to identify customers who potentially become unsatisfied and might lead to escalations. Today this prioritization of customers is often done manually. Data science on IoT data (esp. log data) for machine health monitoring, as well as analytics on enterprise data for customer relationship management (CRM) have mainly been researched and applied independently. In this paper, we present a framework for a data-driven decision support system which combines IoT and enterprise data to model customer sentiment. Such decision support systems can help to prioritize customers and service resources to effectively troubleshoot problems or even avoid them. The framework is applied in a real-world case study with a major medical device manufacturer. This includes a fully automated and interpretable machine learning pipeline designed to meet the requirements defined with domain experts and end users. The overall framework is currently deployed, learns and evaluates predictive models from terabytes of IoT and enterprise data to actively monitor the customer sentiment for a fleet of thousands of high-end medical devices. Furthermore, we provide an anonymized industrial benchmark dataset for the research community.

Leo Schwinn, An Nguyen, René Raab et al.

The vulnerability of deep neural networks to small and even imperceptible perturbations has become a central topic in deep learning research. Although several sophisticated defense mechanisms have been introduced, most were later shown to be ineffective. However, a reliable evaluation of model robustness is mandatory for deployment in safety-critical scenarios. To overcome this problem we propose a simple yet effective modification to the gradient calculation of state-of-the-art first-order adversarial attacks. Normally, the gradient update of an attack is directly calculated for the given data point. This approach is sensitive to noise and small local optima of the loss function. Inspired by gradient sampling techniques from non-convex optimization, we propose Dynamically Sampled Nonlocal Gradient Descent (DSNGD). DSNGD calculates the gradient direction of the adversarial attack as the weighted average over past gradients of the optimization history. Moreover, distribution hyperparameters that define the sampling operation are automatically learned during the optimization scheme. We empirically show that by incorporating this nonlocal gradient information, we are able to give a more accurate estimation of the global descent direction on noisy and non-convex loss surfaces. In addition, we show that DSNGD-based attacks are on average 35% faster while achieving 0.9% to 27.1% higher success rates compared to their gradient descent-based counterparts.

Dario Zanca, Marco Gori, Stefano Melacci et al.

Visual attention refers to the human brain's ability to select relevant sensory information for preferential processing, improving performance in visual and cognitive tasks. It proceeds in two phases. One in which visual feature maps are acquired and processed in parallel. Another where the information from these maps is merged in order to select a single location to be attended for further and more complex computations and reasoning. Its computational description is challenging, especially if the temporal dynamics of the process are taken into account. Numerous methods to estimate saliency have been proposed in the last three decades. They achieve almost perfect performance in estimating saliency at the pixel level, but the way they generate shifts in visual attention fully depends on winner-take-all (WTA) circuitry. WTA is implemented} by the biological hardware in order to select a location with maximum saliency, towards which to direct overt attention. In this paper we propose a gravitational model (GRAV) to describe the attentional shifts. Every single feature acts as an attractor and {the shifts are the result of the joint effects of the attractors. In the current framework, the assumption of a single, centralized saliency map is no longer necessary, though still plausible. Quantitative results on two large image datasets show that this model predicts shifts more accurately than winner-take-all.

Lapo Faggi, Alessandro Betti, Dario Zanca et al.

Fast reactions to changes in the surrounding visual environment require efficient attention mechanisms to reallocate computational resources to most relevant locations in the visual field. While current computational models keep improving their predictive ability thanks to the increasing availability of data, they still struggle approximating the effectiveness and efficiency exhibited by foveated animals. In this paper, we present a biologically-plausible computational model of focus of attention that exhibits spatiotemporal locality and that is very well-suited for parallel and distributed implementations. Attention emerges as a wave propagation process originated by visual stimuli corresponding to details and motion information. The resulting field obeys the principle of "inhibition of return" so as not to get stuck in potential holes. An accurate experimentation of the model shows that it achieves top level performance in scanpath prediction tasks. This can easily be understood at the light of a theoretical result that we establish in the paper, where we prove that as the velocity of wave propagation goes to infinity, the proposed model reduces to recently proposed state of the art gravitational models of focus of attention.

Dario Zanca, Stefano Melacci, Marco Gori

Human visual attention is a complex phenomenon. A computational modeling of this phenomenon must take into account where people look in order to evaluate which are the salient locations (spatial distribution of the fixations), when they look in those locations to understand the temporal development of the exploration (temporal order of the fixations), and how they move from one location to another with respect to the dynamics of the scene and the mechanics of the eyes (dynamics). State-of-the-art models focus on learning saliency maps from human data, a process that only takes into account the spatial component of the phenomenon and ignore its temporal and dynamical counterparts. In this work we focus on the evaluation methodology of models of human visual attention. We underline the limits of the current metrics for saliency prediction and scanpath similarity, and we introduce a statistical measure for the evaluation of the dynamics of the simulated eye movements. While deep learning models achieve astonishing performance in saliency prediction, our analysis shows their limitations in capturing the dynamics of the process. We find that unsupervised gravitational models, despite of their simplicity, outperform all competitors. Finally, exploiting a crowd-sourcing platform, we present a study aimed at evaluating how strongly the scanpaths generated with the unsupervised gravitational models appear plausible to naive and expert human observers.

Dario Zanca, Alessandra Rufa

It is well known that a systematic analysis of the pupil size variations, recorded by means of an eye-tracker, is a rich source of information about a subject's arousal and cognitive state. Current methods for pupil analysis are limited to descriptive statistics, struggle in handling the wide inter-subjects variability and must be coupled with a long series of pre-processing signal operations. In this we present a data-driven approach in which 1-D Convolutional Neural Networks are applied directly to the raw pupil size data. To test its effectiveness, we apply our method in a binary classification task with two different groups of subjects: a group of elderly patients with Parkinson disease (PDs), a condition in which pupil abnormalities have been extensively reported, and a group of healthy adults subjects (HCs). Long-range registration (10 minutes) of the pupil size were collected in scotopic conditions (complete darkness, 0 lux). 1-D convolutional neural network models are trained for classification of short-range sequences (10 to 60 seconds of registration). The model provides prediction with high average accuracy on a hold out test set. Dataset and codes are released for reproducibility and benchmarking purposes.

Alessandro Rossi, Sara Ermini, Dario Bernabini et al.

While theories postulating a dual cognitive system take hold, quantitative confirmations are still needed to understand and identify interactions between the two systems or conflict events. Eye movements are among the most direct markers of the individual attentive load and may serve as an important proxy of information. In this work we propose a computational method, within a modified visual version of the well-known Stroop test, for the identification of different tasks and potential conflicts events between the two systems through the collection and processing of data related to eye movements. A statistical analysis shows that the selected variables can characterize the variation of attentive load within different scenarios. Moreover, we show that Machine Learning techniques allow to distinguish between different tasks with a good classification accuracy and to investigate more in depth the gaze dynamics.

Giuseppe Marra, Dario Zanca, Alessandro Betti et al.

The effectiveness of deep neural architectures has been widely supported in terms of both experimental and foundational principles. There is also clear evidence that the activation function (e.g. the rectifier and the LSTM units) plays a crucial role in the complexity of learning. Based on this remark, this paper discusses an optimal selection of the neuron non-linearity in a functional framework that is inspired from classic regularization arguments. It is shown that the best activation function is represented by a kernel expansion in the training set, that can be effectively approximated over an opportune set of points modeling 1-D clusters. The idea can be naturally extended to recurrent networks, where the expressiveness of kernel-based activation functions turns out to be a crucial ingredient to capture long-term dependencies. We give experimental evidence of this property by a set of challenging experiments, where we compare the results with neural architectures based on state of the art LSTM cells.

Dario Zanca, Marco Gori

The understanding of where humans look in a scene is a problem of great interest in visual perception and computer vision. When eye-tracking devices are not a viable option, models of human attention can be used to predict fixations. In this paper we give two contribution. First, we show a model of visual attention that is simply based on deep convolutional neural networks trained for object classification tasks. A method for visualizing saliency maps is defined which is evaluated in a saliency prediction task. Second, we integrate the information of these maps with a bottom-up differential model of eye-movements to simulate visual attention scanpaths. Results on saliency prediction and scores of similarity with human scanpaths demonstrate the effectiveness of this model.

Dario Zanca, Valeria Serchi, Pietro Piu et al.

In the last three decades, human visual attention has been a topic of great interest in various disciplines. In computer vision, many models have been proposed to predict the distribution of human fixations on a visual stimulus. Recently, thanks to the creation of large collections of data, machine learning algorithms have obtained state-of-the-art performance on the task of saliency map estimation. On the other hand, computational models of scanpath are much less studied. Works are often only descriptive or task specific. This is due to the fact that the scanpath is harder to model because it must include the description of a dynamic. General purpose computational models are present in the literature, but are then evaluated in tasks of saliency prediction, losing therefore information about the dynamics and the behaviour. In addition, two technical reasons have limited the research. The first reason is the lack of robust and uniformly used set of metrics to compare the similarity between scanpath. The second reason is the lack of sufficiently large and varied scanpath datasets. In this report we want to help in both directions. We present FixaTons, a large collection of datasets human scanpaths (temporally ordered sequences of fixations) and saliency maps. It comes along with a software library for easy data usage, statistics calculation and implementation of metrics for scanpath and saliency prediction evaluation.

Francesco Giannini, Vincenzo Laveglia, Alessandro Rossi et al.

This report provides an introduction to some Machine Learning tools within the most common development environments. It mainly focuses on practical problems, skipping any theoretical introduction. It is oriented to both students trying to approach Machine Learning and experts looking for new frameworks.