Search

In image generation, Multiple Latent Variable Generative Models (MLVGMs) employ multiple latent variables to gradually shape the final images, from global characteristics to finer and local details (e.g., StyleGAN, NVAE), emerging as powerful tools for diverse applications. Yet their generative dynamics and latent variable utilization remain only empirically observed. In this work, we propose a novel framework to systematically quantify the impact of each latent variable in MLVGMs, using Mutual Information (MI) as a guiding metric. Our analysis reveals underutilized variables and can guide the use of MLVGMs in downstream applications. With this foundation, we introduce a method for generating synthetic data for Self-Supervised Contrastive Representation Learning (SSCRL). By leveraging the hierarchical and disentangled variables of MLVGMs, and guided by the previous analysis, we apply tailored latent perturbations to produce diverse views for SSCRL, without relying on real data altogether. Additionally, we introduce a Continuous Sampling (CS) strategy, where the generator dynamically creates new samples during SSCRL training, greatly increasing data variability. Our comprehensive experiments demonstrate the effectiveness of these contributions, showing that MLVGMs' generated views compete on par with or even surpass views generated from real data. This work establishes a principled approach to understanding and exploiting MLVGMs, advancing both generative modeling and self-supervised learning.

The fast fashion industry's insatiable demand for new styles and rapid production cycles has led to a significant environmental burden. Overproduction, excessive waste, and harmful chemicals have contributed to the negative environmental impact of the industry. To mitigate these issues, a paradigm shift that prioritizes sustainability and efficiency is urgently needed. Integrating learning-based predictive analytics into the fashion industry represents a significant opportunity to address environmental challenges and drive sustainable practices. By forecasting fashion trends and optimizing production, brands can reduce their ecological footprint while remaining competitive in a rapidly changing market. However, one of the key challenges in forecasting fashion sales is the dynamic nature of consumer preferences. Fashion is acyclical, with trends constantly evolving and resurfacing. In addition, cultural changes and unexpected events can disrupt established patterns. This problem is also known as New Fashion Products Performance Forecasting (NFPPF), and it has recently gained more and more interest in the global research landscape. Given its multidisciplinary nature, the field of NFPPF has been approached from many different angles. This comprehensive survey wishes to provide an up-to-date overview that focuses on learning-based NFPPF strategies. The survey is based on the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodological flow, allowing for a systematic and complete literature review. In particular, we propose the first taxonomy that covers the learning panorama for NFPPF, examining in detail the different methodologies used to increase the amount of multimodal information, as well as the state-of-the-art available datasets. Finally, we discuss the challenges and future directions., Comment: Accepted at the Springer Nature Computer Science journal

The fast fashion industry suffers from significant environmental impacts due to overproduction and unsold inventory. Accurately predicting sales volumes for unreleased products could significantly improve efficiency and resource utilization. However, predicting performance for entirely new items is challenging due to the lack of historical data and rapidly changing trends, and existing deterministic models often struggle with domain shifts when encountering items outside the training data distribution. The recently proposed diffusion models address this issue using a continuous-time diffusion process. This allows us to simulate how new items are adopted, reducing the impact of domain shift challenges faced by deterministic models. As a result, in this paper, we propose MDiFF: a novel two-step multimodal diffusion models-based pipeline for New Fashion Product Performance Forecasting (NFPPF). First, we use a score-based diffusion model to predict multiple future sales for different clothes over time. Then, we refine these multiple predictions with a lightweight Multi-layer Perceptron (MLP) to get the final forecast. MDiFF leverages the strengths of both architectures, resulting in the most accurate and efficient forecasting system for the fast-fashion industry at the state-of-the-art. The code can be found at https://github.com/intelligolabs/MDiFF., Comment: Accepted at the FashionAI workshop @ the European Conference on Computer Vision (ECCV) 2024. arXiv admin note: substantial text overlap with arXiv:2412.05566

In the fast-fashion industry, overproduction and unsold inventory create significant environmental problems. Precise sales forecasts for unreleased items could drastically improve the efficiency and profits of industries. However, predicting the success of entirely new styles is difficult due to the absence of past data and ever-changing trends. Specifically, currently used deterministic models struggle with domain shifts when encountering items outside their training data. The recently proposed diffusion models address this issue using a continuous-time diffusion process. Specifically, these models enable us to predict the sales of new items, mitigating the domain shift challenges encountered by deterministic models. As a result, this paper proposes Dif4FF, a novel two-stage pipeline for New Fashion Product Performance Forecasting (NFPPF) that leverages the power of diffusion models conditioned on multimodal data related to specific clothes. Dif4FF first utilizes a multimodal score-based diffusion model to forecast multiple sales trajectories for various garments over time. The forecasts are refined using a powerful Graph Convolutional Network (GCN) architecture. By leveraging the GCN's capability to capture long-range dependencies within both the temporal and spatial data and seeking the optimal solution between these two dimensions, Dif4FF offers the most accurate and efficient forecasting system available in the literature for predicting the sales of new items. We tested Dif4FF on VISUELLE, the de facto standard for NFPPF, achieving new state-of-the-art results., Comment: Accepted at the 27th International Conference on Pattern Recognition (ICPR 2024)

Attackers can deliberately perturb classifiers' input with subtle noise, altering final predictions. Among proposed countermeasures, adversarial purification employs generative networks to preprocess input images, filtering out adversarial noise. In this study, we propose specific generators, defined Multiple Latent Variable Generative Models (MLVGMs), for adversarial purification. These models possess multiple latent variables that naturally disentangle coarse from fine features. Taking advantage of these properties, we autoencode images to maintain class-relevant information, while discarding and re-sampling any detail, including adversarial noise. The procedure is completely training-free, exploring the generalization abilities of pre-trained MLVGMs on the adversarial purification downstream task. Despite the lack of large models, trained on billions of samples, we show that smaller MLVGMs are already competitive with traditional methods, and can be used as foundation models. Official code released at https://github.com/SerezD/gen_adversarial.

Existing embodied instance goal navigation tasks, driven by natural language, assume human users to provide complete and nuanced instance descriptions prior to the navigation, which can be impractical in the real world as human instructions might be brief and ambiguous. To bridge this gap, we propose a new task, Collaborative Instance Navigation (CoIN), with dynamic agent-human interaction during navigation to actively resolve uncertainties about the target instance in natural, template-free, open-ended dialogues. To address CoIN, we propose a novel method, Agent-user Interaction with UncerTainty Awareness (AIUTA), leveraging the perception capability of Vision Language Models (VLMs) and the capability of Large Language Models (LLMs). First, upon object detection, a Self-Questioner model initiates a self-dialogue to obtain a complete and accurate observation description, while a novel uncertainty estimation technique mitigates inaccurate VLM perception. Then, an Interaction Trigger module determines whether to ask a question to the user, continue or halt navigation, minimizing user input. For evaluation, we introduce CoIN-Bench, a benchmark supporting both real and simulated humans. AIUTA achieves competitive performance in instance navigation against state-of-the-art methods, demonstrating great flexibility in handling user inputs., Comment: https://intelligolabs.github.io/CoIN/

In this position paper, we propose an approach for sustainable data collection in the field of optimal mix design for marble sludge reuse. Marble sludge, a calcium-rich residual from stone-cutting processes, can be repurposed by mixing it with various ingredients. However, determining the optimal mix design is challenging due to the variability in sludge composition and the costly, time-consuming nature of experimental data collection. Also, we investigate the possibility of using machine learning models using meta-learning as an optimization tool to estimate the correct quantity of stone-cutting sludge to be used in aggregates to obtain a mix design with specific mechanical properties that can be used successfully in the building industry. Our approach offers two key advantages: (i) through simulations, a large dataset can be generated, saving time and money during the data collection phase, and (ii) Utilizing machine learning models, with performance enhancement through hyper-parameter optimization via meta-learning, to estimate optimal mix designs reducing the need for extensive manual experimentation, lowering costs, minimizing environmental impact, and accelerating the processing of quarry sludge. Our idea promises to streamline the marble sludge reuse process by leveraging collective data and advanced machine learning, promoting sustainability and efficiency in the stonecutting sector.

Ge'ez, an ancient Ethiopic script of cultural and historical significance, has been largely neglected in handwriting recognition research, hindering the digitization of valuable manuscripts. Our study addresses this gap by developing a state-of-the-art Ge'ez handwriting recognition system using Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks. Our approach uses a two-stage recognition process. First, a CNN is trained to recognize individual characters, which then acts as a feature extractor for an LSTM-based system for word recognition. Our dual-stage recognition approach achieves new top scores in Ge'ez handwriting recognition, outperforming eight state-of-the-art methods, which are SVTR, ASTER, and others as well as human performance, as measured in the HHD-Ethiopic dataset work. This research significantly advances the preservation and accessibility of Ge'ez cultural heritage, with implications for historical document digitization, educational tools, and cultural preservation. The code will be released upon acceptance.

Continuous monitoring of coma patients is essential but challenging, especially in developing countries with limited resources, staff, and infrastructure. This paper presents a low-cost IoT-based system designed for such environments. It uses affordable hardware and robust software to monitor patients without constant internet access or extensive medical personnel. The system employs cost-effective sensors to track vital signs, including heart rate, body temperature, blood pressure, eye movement, and body position. An energy-efficient microcontroller processes data locally, synchronizing with a central server when network access is available. A locally hosted app provides on-site access to patient data, while a GSM module sends immediate alerts for critical events, even in areas with limited cellular coverage. This solution emphasizes ease of deployment, minimal maintenance, and resilience to power and network disruptions. Using open-source software and widely available hardware, it offers a scalable, adaptable system for resource-limited settings. At under $30, the system is a sustainable, cost-effective solution for continuous patient monitoring, bridging the gap until more advanced healthcare infrastructure is available.

Gaze Target Detection (GTD), i.e., determining where a person is looking within a scene from an external viewpoint, is a challenging task, particularly in 3D space. Existing approaches heavily rely on analyzing the person's appearance, primarily focusing on their face to predict the gaze target. This paper presents a novel approach to tackle this problem by utilizing the person's upper-body pose and available depth maps to extract a 3D gaze direction and employing a multi-stage or an end-to-end pipeline to predict the gazed target. When predicted accurately, the human body pose can provide valuable information about the head pose, which is a good approximation of the gaze direction, as well as the position of the arms and hands, which are linked to the activity the person is performing and the objects they are likely focusing on. Consequently, in addition to performing gaze estimation in 3D, we are also able to perform GTD simultaneously. We demonstrate state-of-the-art results on the most comprehensive publicly accessible 3D gaze target detection dataset without requiring images of the person's face, thus promoting privacy preservation in various application contexts. The code is available at https://github.com/intelligolabs/privacy-gtd-3D., Comment: Accepted in the T-CAP workshop at ECCV 2024

In recent years, the development of deep learning approaches for the task of person re-identification led to impressive results. However, this comes with a limitation for industrial and practical real-world applications. Firstly, most of the existing works operate on closed-world scenarios, in which the people to re-identify (probes) are compared to a closed-set (gallery). Real-world scenarios often are open-set problems in which the gallery is not known a priori, but the number of open-set approaches in the literature is significantly lower. Secondly, challenges such as multi-camera setups, occlusions, real-time requirements, etc., further constrain the applicability of off-the-shelf methods. This work presents MICRO-TRACK, a Modular Industrial multi-Camera Re_identification and Open-set Tracking system that is real-time, scalable, and easy to integrate into existing industrial surveillance scenarios. Furthermore, we release a novel Re-ID and tracking dataset acquired in an industrial manufacturing facility, dubbed Facility-ReID, consisting of 18-minute videos captured by 8 surveillance cameras., Comment: Accepted at T-CAP workshop at ECCV 2024

Patterns of human motion in outdoor and indoor environments are substantially different due to the scope of the environment and the typical intentions of people therein. While outdoor trajectory forecasting has received significant attention, indoor forecasting is still an underexplored research area. This paper proposes SITUATE, a novel approach to cope with indoor human trajectory prediction by leveraging equivariant and invariant geometric features and a self-supervised vision representation. The geometric learning modules model the intrinsic symmetries and human movements inherent in indoor spaces. This concept becomes particularly important because self-loops at various scales and rapid direction changes often characterize indoor trajectories. On the other hand, the vision representation module is used to acquire spatial-semantic information about the environment to predict users' future locations more accurately. We evaluate our method through comprehensive experiments on the two most famous indoor trajectory forecasting datasets, i.e., TH\"OR and Supermarket, obtaining state-of-the-art performance. Furthermore, we also achieve competitive results in outdoor scenarios, showing that indoor-oriented forecasting models generalize better than outdoor-oriented ones. The source code is available at https://github.com/intelligolabs/SITUATE., Comment: Accepted at the 27th International Conference on Pattern Recognition (ICPR 2024)

This study introduces the Iterative Refinement Process (IRP), a robust anomaly detection methodology designed for high-stakes industrial quality control. The IRP enhances defect detection accuracy through a cyclic data refinement strategy, iteratively removing misleading data points to improve model performance and robustness. We validate the IRP's effectiveness using two benchmark datasets, Kolektor SDD2 (KSDD2) and MVTec AD, covering a wide range of industrial products and defect types. Our experimental results demonstrate that the IRP consistently outperforms traditional anomaly detection models, particularly in environments with high noise levels. This study highlights the IRP's potential to significantly enhance anomaly detection processes in industrial settings, effectively managing the challenges of sparse and noisy data.

In the past decade, Deep Neural Networks (DNNs) achieved state-of-the-art performance in a broad range of problems, spanning from object classification and action recognition to smart building and healthcare. The flexibility that makes DNNs such a pervasive technology comes at a price: the computational requirements preclude their deployment on most of the resource-constrained edge devices available today to solve real-time and real-world tasks. This paper introduces a novel approach to address this challenge by combining the concept of predefined sparsity with Split Computing (SC) and Early Exit (EE). In particular, SC aims at splitting a DNN with a part of it deployed on an edge device and the rest on a remote server. Instead, EE allows the system to stop using the remote server and rely solely on the edge device's computation if the answer is already good enough. Specifically, how to apply such a predefined sparsity to a SC and EE paradigm has never been studied. This paper studies this problem and shows how predefined sparsity significantly reduces the computational, storage, and energy burdens during the training and inference phases, regardless of the hardware platform. This makes it a valuable approach for enhancing the performance of SC and EE applications. Experimental results showcase reductions exceeding 4x in storage and computational complexity without compromising performance. The source code is available at https://github.com/intelligolabs/sparsity_sc_ee., Comment: Accepted at the 27th Forum on specification and Design Languages (FDL 2024)

Many-body eigenstates that are neither thermal nor many-body-localized (MBL) were numerically found in certain interacting chains with moderate quasiperiodic potentials. The energy regime consisting of these non-ergodic but extended (NEE) eigenstates has been extensively studied for being a possible many-body mobility edge between the energy-resolved MBL and thermal phases. Recently, the NEE regime was further proposed to be a prethermal phenomenon that generally occurs when different operators spread at sizably different timescales. Here, we numerically examine the mutual independence among the NEE, MBL, and thermal regimes in the lens of eigenstate entanglement spectra (ES). Given the complexity and rich information embedded in ES, we develop an unsupervised learning approach that is designed to quantify the mutual independence among general phases. Our method is first demonstrated on an illustrative toy example that uses RGB color data to represent phases, then applied to the ES of an interacting generalized Aubry Andre model from weak to strong potential strength. We find that while the MBL and thermal regimes are mutually independent, the NEE regime is dependent on the former two and smoothly appears as the potential strength decreases. We attribute our numerically finding to the fact that the ES data in the NEE regime exhibits both an MBL-like fast decay and a thermal-like long tail., Comment: 6 pages, 5 figures

Split Computing (SC), where a Deep Neural Network (DNN) is intelligently split with a part of it deployed on an edge device and the rest on a remote server is emerging as a promising approach. It allows the power of DNNs to be leveraged for latency-sensitive applications that do not allow the entire DNN to be deployed remotely, while not having sufficient computation bandwidth available locally. In many such embedded systems scenarios, such as those in the automotive domain, computational resource constraints also necessitate Multi-Task Learning (MTL), where the same DNN is used for multiple inference tasks instead of having dedicated DNNs for each task, which would need more computing bandwidth. However, how to partition such a multi-tasking DNN to be deployed within a SC framework has not been sufficiently studied. This paper studies this problem, and MTL-Split, our novel proposed architecture, shows encouraging results on both synthetic and real-world data. The source code is available at https://github.com/intelligolabs/MTL-Split., Comment: Accepted at the 61st Design Automation Conference (DAC 2024)

Defect detection is the task of identifying defects in production samples. Usually, defect detection classifiers are trained on ground-truth data formed by normal samples (negative data) and samples with defects (positive data), where the latter are consistently fewer than normal samples. State-of-the-art data augmentation procedures add synthetic defect data by superimposing artifacts to normal samples to mitigate problems related to unbalanced training data. These techniques often produce out-of-distribution images, resulting in systems that learn what is not a normal sample but cannot accurately identify what a defect looks like. In this work, we introduce DIAG, a training-free Diffusion-based In-distribution Anomaly Generation pipeline for data augmentation. Unlike conventional image generation techniques, we implement a human-in-the-loop pipeline, where domain experts provide multimodal guidance to the model through text descriptions and region localization of the possible anomalies. This strategic shift enhances the interpretability of results and fosters a more robust human feedback loop, facilitating iterative improvements of the generated outputs. Remarkably, our approach operates in a zero-shot manner, avoiding time-consuming fine-tuning procedures while achieving superior performance. We demonstrate the efficacy and versatility of DIAG with respect to state-of-the-art data augmentation approaches on the challenging KSDD2 dataset, with an improvement in AP of approximately 18% when positive samples are available and 28% when they are missing. The source code is available at https://github.com/intelligolabs/DIAG., Comment: Accepted at the 21st International Conference on Content-Based Multimedia Indexing (CBMI 2024)

In the Vision-and-Language Navigation in Continuous Environments (VLN-CE) task, the human user guides an autonomous agent to reach a target goal via a series of low-level actions following a textual instruction in natural language. However, most existing methods do not address the likely case where users may make mistakes when providing such instruction (e.g. "turn left" instead of "turn right"). In this work, we address a novel task of Interactive VLN in Continuous Environments (IVLN-CE), which allows the agent to interact with the user during the VLN-CE navigation to verify any doubts regarding the instruction errors. We propose an Interactive Instruction Error Detector and Localizer (I2EDL) that triggers the user-agent interaction upon the detection of instruction errors during the navigation. We leverage a pre-trained module to detect instruction errors and pinpoint them in the instruction by cross-referencing the textual input and past observations. In such way, the agent is able to query the user for a timely correction, without demanding the user's cognitive load, as we locate the probable errors to a precise part of the instruction. We evaluate the proposed I2EDL on a dataset of instructions containing errors, and further devise a novel metric, the Success weighted by Interaction Number (SIN), to reflect both the navigation performance and the interaction effectiveness. We show how the proposed method can ask focused requests for corrections to the user, which in turn increases the navigation success, while minimizing the interactions., Comment: Accepted at IEEE RO-MAN 2024

In this study, we show that diffusion models can be used in industrial scenarios to improve the data augmentation procedure in the context of surface defect detection. In general, defect detection classifiers are trained on ground-truth data formed by normal samples (negative data) and samples with defects (positive data), where the latter are consistently fewer than normal samples. For these reasons, state-of-the-art data augmentation procedures add synthetic defect data by superimposing artifacts to normal samples. This leads to out-of-distribution augmented data so that the classification system learns what is not a normal sample but does not know what a defect really is. We show that diffusion models overcome this situation, providing more realistic in-distribution defects so that the model can learn the defect's genuine appearance. We propose a novel approach for data augmentation that mixes out-of-distribution with in-distribution samples, which we call In&Out. The approach can deal with two data augmentation setups: i) when no defects are available (zero-shot data augmentation) and ii) when defects are available, which can be in a small number (few-shot) or a large one (full-shot). We focus the experimental part on the most challenging benchmark in the state-of-the-art, i.e., the Kolektor Surface-Defect Dataset 2, defining the new state-of-the-art classification AP score under weak supervision of .782. The code is available at https://github.com/intelligolabs/in_and_out., Comment: Accepted at the 19th International Conference on Computer Vision Theory and Applications (VISAPP 2024)

We introduce HARPER, a novel dataset for 3D body pose estimation and forecast in dyadic interactions between users and Spot, the quadruped robot manufactured by Boston Dynamics. The key-novelty is the focus on the robot's perspective, i.e., on the data captured by the robot's sensors. These make 3D body pose analysis challenging because being close to the ground captures humans only partially. The scenario underlying HARPER includes 15 actions, of which 10 involve physical contact between the robot and users. The Corpus contains not only the recordings of the built-in stereo cameras of Spot, but also those of a 6-camera OptiTrack system (all recordings are synchronized). This leads to ground-truth skeletal representations with a precision lower than a millimeter. In addition, the Corpus includes reproducible benchmarks on 3D Human Pose Estimation, Human Pose Forecasting, and Collision Prediction, all based on publicly available baseline approaches. This enables future HARPER users to rigorously compare their results with those we provide in this work.

Vision-and-Language Navigation in Continuous Environments (VLN-CE) is one of the most intuitive yet challenging embodied AI tasks. Agents are tasked to navigate towards a target goal by executing a set of low-level actions, following a series of natural language instructions. All VLN-CE methods in the literature assume that language instructions are exact. However, in practice, instructions given by humans can contain errors when describing a spatial environment due to inaccurate memory or confusion. Current VLN-CE benchmarks do not address this scenario, making the state-of-the-art methods in VLN-CE fragile in the presence of erroneous instructions from human users. For the first time, we propose a novel benchmark dataset that introduces various types of instruction errors considering potential human causes. This benchmark provides valuable insight into the robustness of VLN systems in continuous environments. We observe a noticeable performance drop (up to -25%) in Success Rate when evaluating the state-of-the-art VLN-CE methods on our benchmark. Moreover, we formally define the task of Instruction Error Detection and Localization, and establish an evaluation protocol on top of our benchmark dataset. We also propose an effective method, based on a cross-modal transformer architecture, that achieves the best performance in error detection and localization, compared to baselines. Surprisingly, our proposed method has revealed errors in the validation set of the two commonly used datasets for VLN-CE, i.e., R2R-CE and RxR-CE, demonstrating the utility of our technique in other tasks. Code and dataset available at https://intelligolabs.github.io/R2RIE-CE, Comment: 3 figures, 8 pages. Accepted at IROS'24

Auxiliary tasks facilitate learning in situations when data is scarce or the principal task of focus is extremely complex. This idea is primarily inspired by the improved generalization capability induced by solving multiple tasks simultaneously, which leads to a more robust shared representation. Nevertheless, finding optimal auxiliary tasks is a crucial problem that often requires hand-crafted solutions or expensive meta-learning approaches. In this paper, we propose a novel framework, dubbed Detaux, whereby a weakly supervised disentanglement procedure is used to discover a new unrelated auxiliary classification task, which allows us to go from a Single-Task Learning (STL) to a Multi-Task Learning (MTL) problem. The disentanglement procedure works at the representation level, isolating the variation related to the principal task into an isolated subspace and additionally producing an arbitrary number of orthogonal subspaces, each one of them encouraging high separability among the projections. We generate the auxiliary classification task through a clustering procedure on the most disentangled subspace, obtaining a discrete set of labels. Subsequently, the original data, the labels associated with the principal task, and the newly discovered ones can be fed into any MTL framework. Experimental validation on both synthetic and real data, along with various ablation studies, demonstrate promising results, revealing the potential in what has been, so far, an unexplored connection between learning disentangled representations and MTL. The source code will be made available upon acceptance.

Joint-Embedding Predictive Architectures (JEPAs) have recently emerged as a novel and powerful technique for self-supervised representation learning. They aim to learn an energy-based model by predicting the latent representation of a target signal y from the latent representation of a context signal x. JEPAs bypass the need for negative and positive samples, traditionally required by contrastive learning while avoiding the overfitting issues associated with generative pretraining. In this paper, we show that graph-level representations can be effectively modeled using this paradigm by proposing a Graph Joint-Embedding Predictive Architecture (Graph-JEPA). In particular, we employ masked modeling and focus on predicting the latent representations of masked subgraphs starting from the latent representation of a context subgraph. To endow the representations with the implicit hierarchy that is often present in graph-level concepts, we devise an alternative prediction objective that consists of predicting the coordinates of the encoded subgraphs on the unit hyperbola in the 2D plane. Through multiple experimental evaluations, we show that Graph-JEPA can learn highly semantic and expressive representations, as shown by the downstream performance in graph classification, regression, and distinguishing non-isomorphic graphs. The code is available at https://github.com/geriskenderi/graph-jepa., Comment: Accepted in Transactions of Machine Learning Research (TMLR)

The emergence of Tiny Machine Learning (TinyML) has positively revolutionized the field of Artificial Intelligence by promoting the joint design of resource-constrained IoT hardware devices and their learning-based software architectures. TinyML carries an essential role within the fourth and fifth industrial revolutions in helping societies, economies, and individuals employ effective AI-infused computing technologies (e.g., smart cities, automotive, and medical robotics). Given its multidisciplinary nature, the field of TinyML has been approached from many different angles: this comprehensive survey wishes to provide an up-to-date overview focused on all the learning algorithms within TinyML-based solutions. The survey is based on the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodological flow, allowing for a systematic and complete literature survey. In particular, firstly we will examine the three different workflows for implementing a TinyML-based system, i.e., ML-oriented, HW-oriented, and co-design. Secondly, we propose a taxonomy that covers the learning panorama under the TinyML lens, examining in detail the different families of model optimization and design, as well as the state-of-the-art learning techniques. Thirdly, this survey will present the distinct features of hardware devices and software tools that represent the current state-of-the-art for TinyML intelligent edge applications. Finally, we discuss the challenges and future directions., Comment: Article currently under review at IEEE Access

We present Le-RNR-Map, a Language-enhanced Renderable Neural Radiance map for Visual Navigation with natural language query prompts. The recently proposed RNR-Map employs a grid structure comprising latent codes positioned at each pixel. These latent codes, which are derived from image observation, enable: i) image rendering given a camera pose, since they are converted to Neural Radiance Field; ii) image navigation and localization with astonishing accuracy. On top of this, we enhance RNR-Map with CLIP-based embedding latent codes, allowing natural language search without additional label data. We evaluate the effectiveness of this map in single and multi-object searches. We also investigate its compatibility with a Large Language Model as an "affordance query resolver". Code and videos are available at https://intelligolabs.github.io/Le-RNR-Map/, Comment: Accepted at ICCVW23 VLAR

Industry 4.0 involves the integration of digital technologies, such as IoT, Big Data, and AI, into manufacturing and industrial processes to increase efficiency and productivity. As these technologies become more interconnected and interdependent, Industry 4.0 systems become more complex, which brings the difficulty of identifying and stopping anomalies that may cause disturbances in the manufacturing process. This paper aims to propose a diffusion-based model for real-time anomaly prediction in Industry 4.0 processes. Using a neuro-symbolic approach, we integrate industrial ontologies in the model, thereby adding formal knowledge on smart manufacturing. Finally, we propose a simple yet effective way of distilling diffusion models through Random Fourier Features for deployment on an embedded system for direct integration into the manufacturing process. To the best of our knowledge, this approach has never been explored before., Comment: Accepted at the 26th Forum on specification and Design Languages (FDL 2023)

Continuous mid-air hand gesture recognition based on captured hand pose streams is fundamental for human-computer interaction, particularly in AR / VR. However, many of the methods proposed to recognize heterogeneous hand gestures are tested only on the classification task, and the real-time low-latency gesture segmentation in a continuous stream is not well addressed in the literature. For this task, we propose the On-Off deep Multi-View Multi-Task paradigm (OO-dMVMT). The idea is to exploit multiple time-local views related to hand pose and movement to generate rich gesture descriptions, along with using heterogeneous tasks to achieve high accuracy. OO-dMVMT extends the classical MVMT paradigm, where all of the multiple tasks have to be active at each time, by allowing specific tasks to switch on/off depending on whether they can apply to the input. We show that OO-dMVMT defines the new SotA on continuous/online 3D skeleton-based gesture recognition in terms of gesture classification accuracy, segmentation accuracy, false positives, and decision latency while maintaining real-time operation., Comment: Accepted to the Computer Vision for Mixed Reality workshop at CVPR 2023

BDDs are representations of a Boolean expression in the form of a directed acyclic graph. BDDs are widely used in several fields, particularly in model checking and hardware verification. There are several implementations for BDD manipulation, where each package differs depending on the application. This paper presents HermesBDD: a novel multi-core and multi-platform binary decision diagram package focused on high performance and usability. HermesBDD supports a static and dynamic memory management mechanism, the possibility to exploit lock-free hash tables, and a simple parallel implementation of the If-Then-Else procedure based on a higher-level wrapper for threads and futures. HermesBDD is completely written in C++ with no need to rely on external libraries and is developed according to software engineering principles for reliability and easy maintenance over time. We provide experimental results on the n-Queens problem, the de-facto SAT solver benchmark for BDDs, demonstrating a significant speedup of 18.73x over our non-parallel baselines, and a remarkable performance boost w.r.t. other state-of-the-art BDDs packages., Comment: 26th International Symposium on Design and Diagnostics of Electronic Circuits and Systems (DDECS)

Many recent pattern recognition applications rely on complex distributed architectures in which sensing and computational nodes interact together through a communication network. Deep neural networks (DNNs) play an important role in this scenario, furnishing powerful decision mechanisms, at the price of a high computational effort. Consequently, powerful state-of-the-art DNNs are frequently split over various computational nodes, e.g., a first part stays on an embedded device and the rest on a server. Deciding where to split a DNN is a challenge in itself, making the design of deep learning applications even more complicated. Therefore, we propose Split-Et-Impera, a novel and practical framework that i) determines the set of the best-split points of a neural network based on deep network interpretability principles without performing a tedious try-and-test approach, ii) performs a communication-aware simulation for the rapid evaluation of different neural network rearrangements, and iii) suggests the best match between the quality of service requirements of the application and the performance in terms of accuracy and latency time., Comment: 26th International Symposium on Design and Diagnostics of Electronic Circuits and Systems (DDECS)

We propose a solution for Active Visual Search of objects in an environment, whose 2D floor map is the only known information. Our solution has three key features that make it more plausible and robust to detector failures compared to state-of-the-art methods: (i) it is unsupervised as it does not need any training sessions. (ii) During the exploration, a probability distribution on the 2D floor map is updated according to an intuitive mechanism, while an improved belief update increases the effectiveness of the agent's exploration. (iii) We incorporate the awareness that an object detector may fail into the aforementioned probability modelling by exploiting the success statistics of a specific detector. Our solution is dubbed POMP-BE-PD (Pomcp-based Online Motion Planning with Belief by Exploration and Probabilistic Detection). It uses the current pose of an agent and an RGB-D observation to learn an optimal search policy, exploiting a POMDP solved by a Monte-Carlo planning approach. On the Active Vision Database benchmark, we increase the average success rate over all the environments by a significant 35% while decreasing the average path length by 4% with respect to competing methods. Thus, our results are state-of-the-art, even without using any training procedure., Comment: 12 pages,8 figures. Submitted for review at IEEE Transactions on Pattern Analysis and Machine Intelligence. arXiv admin note: text overlap with arXiv:2009.08140

We propose a novel image dataset focused on tiny faces wearing face masks for mask classification purposes, dubbed Small Face MASK (SF-MASK), composed of a collection made from 20k low-resolution images exported from diverse and heterogeneous datasets, ranging from 7 x 7 to 64 x 64 pixel resolution. An accurate visualization of this collection, through counting grids, made it possible to highlight gaps in the variety of poses assumed by the heads of the pedestrians. In particular, faces filmed by very high cameras, in which the facial features appear strongly skewed, are absent. To address this structural deficiency, we produced a set of synthetic images which resulted in a satisfactory covering of the intra-class variance. Furthermore, a small subsample of 1701 images contains badly worn face masks, opening to multi-class classification challenges. Experiments on SF-MASK focus on face mask classification using several classifiers. Results show that the richness of SF-MASK (real + synthetic images) leads all of the tested classifiers to perform better than exploiting comparative face mask datasets, on a fixed 1077 images testing set. Dataset and evaluation code are publicly available here: https://github.com/HumaticsLAB/sf-mask, Comment: 15 pages, 7 figures. Accepted at T-CAP workshop @ ICPR 2022

The fashion industry is one of the most active and competitive markets in the world, manufacturing millions of products and reaching large audiences every year. A plethora of business processes are involved in this large-scale industry, but due to the generally short life-cycle of clothing items, supply-chain management and retailing strategies are crucial for good market performance. Correctly understanding the wants and needs of clients, managing logistic issues and marketing the correct products are high-level problems with a lot of uncertainty associated to them given the number of influencing factors, but most importantly due to the unpredictability often associated with the future. It is therefore straightforward that forecasting methods, which generate predictions of the future, are indispensable in order to ameliorate all the various business processes that deal with the true purpose and meaning of fashion: having a lot of people wear a particular product or style, rendering these items, people and consequently brands fashionable. In this paper, we provide an overview of three concrete forecasting tasks that any fashion company can apply in order to improve their industrial and market impact. We underline advances and issues in all three tasks and argue about their importance and the impact they can have at an industrial level. Finally, we highlight issues and directions of future work, reflecting on how learning-based forecasting methods can further aid the fashion industry., Comment: 2nd International Workshop on Industrial Machine Learning @ ICPR 2022

We propose an end-to-end solution to address the problem of object localisation in partial scenes, where we aim to estimate the position of an object in an unknown area given only a partial 3D scan of the scene. We propose a novel scene representation to facilitate the geometric reasoning, Directed Spatial Commonsense Graph (D-SCG), a spatial scene graph that is enriched with additional concept nodes from a commonsense knowledge base. Specifically, the nodes of D-SCG represent the scene objects and the edges are their relative positions. Each object node is then connected via different commonsense relationships to a set of concept nodes. With the proposed graph-based scene representation, we estimate the unknown position of the target object using a Graph Neural Network that implements a novel attentional message passing mechanism. The network first predicts the relative positions between the target object and each visible object by learning a rich representation of the objects via aggregating both the object nodes and the concept nodes in D-SCG. These relative positions then are merged to obtain the final position. We evaluate our method using Partial ScanNet, improving the state-of-the-art by 5.9% in terms of the localisation accuracy at a 8x faster training speed., Comment: arXiv admin note: text overlap with arXiv:2203.05380

Conventional automatic doors cannot distinguish between people wishing to pass through the door and people passing by the door, so they often open unnecessarily. This leads to the need to adopt new systems in both commercial and non-commercial environments: smart doors. In particular, a smart door system predicts the intention of people near the door based on the social context of the surrounding environment and then makes rational decisions about whether or not to open the door. This work proposes the first position paper related to smart doors, without bells and whistles. We first point out that the problem not only concerns reliability, climate control, safety, and mode of operation. Indeed, a system to predict the intention of people near the door also involves a deeper understanding of the social context of the scene through a complex combined analysis of proxemics and scene reasoning. Furthermore, we conduct an exhaustive literature review about automatic doors, providing a novel system formulation. Also, we present an analysis of the possible future application of smart doors, a description of the ethical shortcomings, and legislative issues., Comment: 2nd International Workshop on Industrial Machine Learning @ ICPR 2022

The use of meta-rules in logic, i.e., rules whose content includes other rules, has recently gained attention in the setting of non-monotonic reasoning: a first logical formalisation and efficient algorithms to compute the (meta)-extensions of such theories were proposed in Olivieri et al (2021) This work extends such a logical framework by considering the deontic aspect. The resulting logic will not just be able to model policies but also tackle well-known aspects that occur in numerous legal systems. The use of Defeasible Logic (DL) to model meta-rules in the application area we just alluded to has been investigated. Within this line of research, the study mentioned above was not focusing on the general computational properties of meta-rules. This study fills this gap with two major contributions. First, we introduce and formalise two variants of Defeasible Deontic Logic with Meta-Rules to represent (1) defeasible meta-theories with deontic modalities, and (2) two different types of conflicts among rules: Simple Conflict Defeasible Deontic Logic, and Cautious Conflict Defeasible Deontic Logic. Second, we advance efficient algorithms to compute the extensions for both variants.

This work makes a substantial step in the field of split computing, i.e., how to split a deep neural network to host its early part on an embedded device and the rest on a server. So far, potential split locations have been identified exploiting uniquely architectural aspects, i.e., based on the layer sizes. Under this paradigm, the efficacy of the split in terms of accuracy can be evaluated only after having performed the split and retrained the entire pipeline, making an exhaustive evaluation of all the plausible splitting points prohibitive in terms of time. Here we show that not only the architecture of the layers does matter, but the importance of the neurons contained therein too. A neuron is important if its gradient with respect to the correct class decision is high. It follows that a split should be applied right after a layer with a high density of important neurons, in order to preserve the information flowing until then. Upon this idea, we propose Interpretable Split (I-SPLIT): a procedure that identifies the most suitable splitting points by providing a reliable prediction on how well this split will perform in terms of classification accuracy, beforehand of its effective implementation. As a further major contribution of I-SPLIT, we show that the best choice for the splitting point on a multiclass categorization problem depends also on which specific classes the network has to deal with. Exhaustive experiments have been carried out on two networks, VGG16 and ResNet-50, and three datasets, Tiny-Imagenet-200, notMNIST, and Chest X-Ray Pneumonia. The source code is available at https://github.com/vips4/I-Split., Comment: ICPR 2022