Marcello Pelillo

Antonio Emanuele Cinà, Kathrin Grosse, Ambra Demontis et al.

The success of machine learning is fueled by the increasing availability of computing power and large training datasets. The training data is used to learn new models or update existing ones, assuming that it is sufficiently representative of the data that will be encountered at test time. This assumption is challenged by the threat of poisoning, an attack that manipulates the training data to compromise the model's performance at test time. Although poisoning has been acknowledged as a relevant threat in industry applications, and a variety of different attacks and defenses have been proposed so far, a complete systematization and critical review of the field is still missing. In this survey, we provide a comprehensive systematization of poisoning attacks and defenses in machine learning, reviewing more than 100 papers published in the field in the last 15 years. We start by categorizing the current threat models and attacks, and then organize existing defenses accordingly. While we focus mostly on computer-vision applications, we argue that our systematization also encompasses state-of-the-art attacks and defenses for other data modalities. Finally, we discuss existing resources for research in poisoning, and shed light on the current limitations and open research questions in this research field.

Antonio Emanuele Cinà, Kathrin Grosse, Ambra Demontis et al.

The recent success of machine learning (ML) has been fueled by the increasing availability of computing power and large amounts of data in many different applications. However, the trustworthiness of the resulting models can be compromised when such data is maliciously manipulated to mislead the learning process. In this article, we first review poisoning attacks that compromise the training data used to learn ML models, including attacks that aim to reduce the overall performance, manipulate the predictions on specific test samples, and even implant backdoors in the model. We then discuss how to mitigate these attacks using basic security principles, or by deploying ML-oriented defensive mechanisms. We conclude our article by formulating some relevant open challenges which are hindering the development of testing methods and benchmarks suitable for assessing and improving the trustworthiness of ML models against data poisoning attacks

Antonio Emanuele Cinà, Ambra Demontis, Battista Biggio et al.

Sponge examples are test-time inputs optimized to increase energy consumption and prediction latency of deep networks deployed on hardware accelerators. By increasing the fraction of neurons activated during classification, these attacks reduce sparsity in network activation patterns, worsening the performance of hardware accelerators. In this work, we present a novel training-time attack, named sponge poisoning, which aims to worsen energy consumption and prediction latency of neural networks on any test input without affecting classification accuracy. To stage this attack, we assume that the attacker can control only a few model updates during training -- a likely scenario, e.g., when model training is outsourced to an untrusted third party or distributed via federated learning. Our extensive experiments on image classification tasks show that sponge poisoning is effective, and that fine-tuning poisoned models to repair them poses prohibitive costs for most users, highlighting that tackling sponge poisoning remains an open issue.

Dario Lazzaro, Antonio Emanuele Cinà, Maura Pintor et al.

Deep learning models undergo a significant increase in the number of parameters they possess, leading to the execution of a larger number of operations during inference. This expansion significantly contributes to higher energy consumption and prediction latency. In this work, we propose EAT, a gradient-based algorithm that aims to reduce energy consumption during model training. To this end, we leverage a differentiable approximation of the $\ell_0$ norm, and use it as a sparse penalty over the training loss. Through our experimental analysis conducted on three datasets and two deep neural networks, we demonstrate that our energy-aware training algorithm EAT is able to train networks with a better trade-off between classification performance and energy efficiency.

Ismail Elezi, Jenny Seidenschwarz, Laurin Wagner et al.

Deep metric learning has yielded impressive results in tasks such as clustering and image retrieval by leveraging neural networks to obtain highly discriminative feature embeddings, which can be used to group samples into different classes. Much research has been devoted to the design of smart loss functions or data mining strategies for training such networks. Most methods consider only pairs or triplets of samples within a mini-batch to compute the loss function, which is commonly based on the distance between embeddings. We propose Group Loss, a loss function based on a differentiable label-propagation method that enforces embedding similarity across all samples of a group while promoting, at the same time, low-density regions amongst data points belonging to different groups. Guided by the smoothness assumption that "similar objects should belong to the same group", the proposed loss trains the neural network for a classification task, enforcing a consistent labelling amongst samples within a class. We design a set of inference strategies tailored towards our algorithm, named Group Loss++ that further improve the results of our model. We show state-of-the-art results on clustering and image retrieval on four retrieval datasets, and present competitive results on two person re-identification datasets, providing a unified framework for retrieval and re-identification.

Ali Alagrami, Luca Palmieri, Sinem Aslan et al.

Reassembling 3D broken objects is a challenging task. A robust solution that generalizes well must deal with diverse patterns associated with different types of broken objects. We propose a method that tackles the pairwise assembly of 3D point clouds, that is agnostic on the type of object, and that relies solely on their geometrical information, without any prior information on the shape of the reconstructed object. The method receives two point clouds as input and segments them into regions using detected closed boundary contours, known as breaking curves. Possible alignment combinations of the regions of each broken object are evaluated and the best one is selected as the final alignment. Experiments were carried out both on available 3D scanned objects and on a recent benchmark for synthetic broken objects. Results show that our solution performs well in reassembling different kinds of broken objects.

Ben Vardi, Alessandro Torcinovich, Marina Khoroshiltseva et al.

We present a novel method for solving square jigsaw puzzles based on global optimization. The method is fully automatic, assumes no prior information, and can handle puzzles with known or unknown piece orientation. At the core of the optimization process is nonlinear relaxation labeling, a well-founded approach for deducing global solutions from local constraints, but unlike the classical scheme here we propose a multi-phase approach that guarantees convergence to feasible puzzle solutions. Next to the algorithmic novelty, we also present a new compatibility function for the quantification of the affinity between adjacent puzzle pieces. Competitive results and the advantage of the multi-phase approach are demonstrated on standard datasets.

Marina Khoroshiltseva, Arianna Traviglia, Marcello Pelillo et al.

This paper proposes JiGAN, a GAN-based method for solving Jigsaw puzzles with eroded or missing borders. Missing borders is a common real-world situation, for example, when dealing with the reconstruction of broken artifacts or ruined frescoes. In this particular condition, the puzzle's pieces do not align perfectly due to the borders' gaps; in this situation, the patches' direct match is unfeasible due to the lack of color and line continuations. JiGAN, is a two-steps procedure that tackles this issue: first, we repair the eroded borders with a GAN-based image extension model and measure the alignment affinity between pieces; then, we solve the puzzle with the relaxation labeling algorithm to enforce consistency in pieces positioning, hence, reconstructing the puzzle. We test the method on a large dataset of small puzzles and on three commonly used benchmark datasets to demonstrate the feasibility of the proposed approach.

Hebatallah A. Mohamed, Sebastiano Vascon, Feliks Hibraj et al.

Knowledge Graphs (KGs) have proven to be a reliable way of structuring data. They can provide a rich source of contextual information about cultural heritage collections. However, cultural heritage KGs are far from being complete. They are often missing important attributes such as geographical location, especially for sculptures and mobile or indoor entities such as paintings. In this paper, we first present a framework for ingesting knowledge about tangible cultural heritage entities from various data sources and their connected multi-hop knowledge into a geolocalized KG. Secondly, we propose a multi-view learning model for estimating the relative distance between a given pair of cultural heritage entities, based on the geographical as well as the knowledge connections of the entities.

Martina Mattioli, Antonio Emanuele Cinà, Marcello Pelillo

Despite explainable AI (XAI) has recently become a hot topic and several different approaches have been developed, there is still a widespread belief that it lacks a convincing unifying foundation. On the other hand, over the past centuries, the very concept of explanation has been the subject of extensive philosophical analysis in an attempt to address the fundamental question of "why" in the context of scientific law. However, this discussion has rarely been connected with XAI. This paper tries to fill in this gap and aims to explore the concept of explanation in AI through an epistemological lens. By comparing the historical development of both the philosophy of science and AI, an intriguing picture emerges. Specifically, we show that a gradual progression has independently occurred in both domains from logical-deductive to statistical models of explanation, thereby experiencing in both cases a paradigm shift from deterministic to nondeterministic and probabilistic causality. Interestingly, we also notice that similar concepts have independently emerged in both realms such as, for example, the relation between explanation and understanding and the importance of pragmatic factors. Our study aims to be the first step towards understanding the philosophical underpinnings of the notion of explanation in AI, and we hope that our findings will shed some fresh light on the elusive nature of XAI.

Sara Ferro, Alessandro Torcinovich, Arianna Traviglia et al.

The primary challenge for handwriting recognition systems lies in managing long-range contextual dependencies, an issue that traditional models often struggle with. To mitigate it, attention mechanisms have recently been employed to enhance context-aware labelling, thereby achieving state-of-the-art performance. In the field of pattern recognition and image analysis, however, the use of contextual information in labelling problems has a long history and goes back at least to the early 1970's. Among the various approaches developed in those years, Relaxation Labelling (RL) processes have played a prominent role and have been the method of choice in the field for more than a decade. Contrary to recent transformer-based architectures, RL processes offer a principled approach to the use of contextual constraints, having a solid theoretic foundation grounded on variational inequality and game theory, as well as effective algorithms with convergence guarantees. In this paper, we propose a novel approach to handwriting recognition that integrates the strengths of two distinct methodologies. In particular, we propose integrating (trainable) RL processes with various well-established neural architectures and we introduce a sparsification technique that accelerates the convergence of the algorithm and enhances the overall system's performance. Experiments over several benchmark datasets show that RL processes can improve the generalisation ability, even surpassing in some cases transformer-based architectures.

Sebastiano Vascon, Sinem Aslan, Gianluca Bigaglia et al.

Verb Sense Disambiguation is a well-known task in NLP, the aim is to find the correct sense of a verb in a sentence. Recently, this problem has been extended in a multimodal scenario, by exploiting both textual and visual features of ambiguous verbs leading to a new problem, the Visual Verb Sense Disambiguation (VVSD). Here, the sense of a verb is assigned considering the content of an image paired with it rather than a sentence in which the verb appears. Annotating a dataset for this task is more complex than textual disambiguation, because assigning the correct sense to a pair of $<$image, verb$>$ requires both non-trivial linguistic and visual skills. In this work, differently from the literature, the VVSD task will be performed in a transductive semi-supervised learning (SSL) setting, in which only a small amount of labeled information is required, reducing tremendously the need for annotated data. The disambiguation process is based on a graph-based label propagation method which takes into account mono or multimodal representations for $<$image, verb$>$ pairs. Experiments have been carried out on the recently published dataset VerSe, the only available dataset for this task. The achieved results outperform the current state-of-the-art by a large margin while using only a small fraction of labeled samples per sense. Code available: https://github.com/GiBg1aN/TVVSD.

Sebastiano Vascon, Samuel Rota Bulò, Vittorio Murino et al.

DSLib is an open-source implementation of the Dominant Set (DS) clustering algorithm written entirely in Matlab. The DS method is a graph-based clustering technique rooted in the evolutionary game theory that starts gaining lots of interest in the computer science community. Thanks to its duality with game theory and its strict relation to the notion of maximal clique, has been explored in several directions not only related to clustering problems. Applications in graph matching, segmentation, classification and medical imaging are common in literature. This package provides an implementation of the original DS clustering algorithm since no code has been officially released yet, together with a still growing collection of methods and variants related to it. Our library is integrable into a Matlab pipeline without dependencies, it is simple to use and easily extendable for upcoming works. The latest source code, the documentation and some examples can be downloaded from https://xwasco.github.io/DominantSetLibrary.

Chu Wang, Marcello Pelillo, Kaleem Siddiqi

View based strategies for 3D object recognition have proven to be very successful. The state-of-the-art methods now achieve over 90% correct category level recognition performance on appearance images. We improve upon these methods by introducing a view clustering and pooling layer based on dominant sets. The key idea is to pool information from views which are similar and thus belong to the same cluster. The pooled feature vectors are then fed as inputs to the same layer, in a recurrent fashion. This recurrent clustering and pooling module, when inserted in an off-the-shelf pretrained CNN, boosts performance for multi-view 3D object recognition, achieving a new state of the art test set recognition accuracy of 93.8% on the ModelNet 40 database. We also explore a fast approximate learning strategy for our cluster-pooling CNN, which, while sacrificing end-to-end learning, greatly improves its training efficiency with only a slight reduction of recognition accuracy to 93.3%. Our implementation is available at https://github.com/fate3439/dscnn.

Theodore Tsesmelis, Luca Palmieri, Marina Khoroshiltseva et al.

This paper proposes the RePAIR dataset that represents a challenging benchmark to test modern computational and data driven methods for puzzle-solving and reassembly tasks. Our dataset has unique properties that are uncommon to current benchmarks for 2D and 3D puzzle solving. The fragments and fractures are realistic, caused by a collapse of a fresco during a World War II bombing at the Pompeii archaeological park. The fragments are also eroded and have missing pieces with irregular shapes and different dimensions, challenging further the reassembly algorithms. The dataset is multi-modal providing high resolution images with characteristic pictorial elements, detailed 3D scans of the fragments and meta-data annotated by the archaeologists. Ground truth has been generated through several years of unceasing fieldwork, including the excavation and cleaning of each fragment, followed by manual puzzle solving by archaeologists of a subset of approx. 1000 pieces among the 16000 available. After digitizing all the fragments in 3D, a benchmark was prepared to challenge current reassembly and puzzle-solving methods that often solve more simplistic synthetic scenarios. The tested baselines show that there clearly exists a gap to fill in solving this computationally complex problem.

Antonio Emanuele Cinà, Francesco Villani, Maura Pintor et al.

Evaluating the adversarial robustness of deep networks to gradient-based attacks is challenging. While most attacks consider $\ell_2$- and $\ell_\infty$-norm constraints to craft input perturbations, only a few investigate sparse $\ell_1$- and $\ell_0$-norm attacks. In particular, $\ell_0$-norm attacks remain the least studied due to the inherent complexity of optimizing over a non-convex and non-differentiable constraint. However, evaluating adversarial robustness under these attacks could reveal weaknesses otherwise left untested with more conventional $\ell_2$- and $\ell_\infty$-norm attacks. In this work, we propose a novel $\ell_0$-norm attack, called $σ$-zero, which leverages a differentiable approximation of the $\ell_0$ norm to facilitate gradient-based optimization, and an adaptive projection operator to dynamically adjust the trade-off between loss minimization and perturbation sparsity. Extensive evaluations using MNIST, CIFAR10, and ImageNet datasets, involving robust and non-robust models, show that $σ$\texttt{-zero} finds minimum $\ell_0$-norm adversarial examples without requiring any time-consuming hyperparameter tuning, and that it outperforms all competing sparse attacks in terms of success rate, perturbation size, and efficiency.

Marina Khoroshiltseva, Luca Palmieri, Sinem Aslan et al.

Jigsaw puzzle solving is a challenging task for computer vision since it requires high-level spatial and semantic reasoning. To solve the problem, existing approaches invariably use color and/or shape information but in many real-world scenarios, such as in archaeological fresco reconstruction, this kind of clues is often unreliable due to severe physical and pictorial deterioration of the individual fragments. This makes state-of-the-art approaches entirely unusable in practice. On the other hand, in such cases, simple geometrical patterns such as lines or curves offer a powerful yet unexplored clue. In an attempt to fill in this gap, in this paper we introduce a new challenging version of the puzzle solving problem in which one deliberately ignores conventional color and shape features and relies solely on the presence of linear geometrical patterns. The reconstruction process is then only driven by one of the most fundamental principles of Gestalt perceptual organization, namely Wertheimer's {\em law of good continuation}. In order to tackle this problem, we formulate the puzzle solving problem as the problem of finding a Nash equilibrium of a (noncooperative) multiplayer game and use classical multi-population replicator dynamics to solve it. The proposed approach is general and allows us to deal with pieces of arbitrary shape, size and orientation. We evaluate our approach on both synthetic and real-world data and compare it with state-of-the-art algorithms. The results show the intrinsic complexity of our purely line-based puzzle problem as well as the relative effectiveness of our game-theoretic formulation.

Omidreza Safaei, Sinem Aslan, Sebastiano Vascon et al.

Reassembling real-world archaeological artifacts from fragmented pieces poses significant challenges due to erosion, missing regions, irregular shapes, and large-scale ambiguity. Traditional jigsaw puzzle solvers, often designed for clean synthetic scenarios, struggle under these conditions, especially when the number of fragments grows into the thousands, as in the RePAIR benchmark. In this paper, we propose a human-in-the-loop (HIL) puzzle solving framework designed to address the complexity and scale of real-world cultural heritage reconstruction. Our approach integrates an automatic relaxation-labeling solver with interactive human guidance, allowing users to iteratively lock verified placements, correct errors, and guide the system toward semantically and geometrically coherent assemblies. We introduce two complementary interaction strategies, Iterative Anchoring and Continuous Interactive Refinement, which support scalable reconstruction across varying levels of ambiguity and puzzle size. Experiments on several RePAIR groups demonstrate that our hybrid approach substantially outperforms both fully automatic and manual baselines in accuracy and efficiency, offering a practical solution for large-scale expert-in-the-loop artifact reassembly.

Martina Mattioli, Eike Petersen, Aasa Feragen et al.

Artificial intelligence (AI) is being applied in almost every field. At the same time, the currently dominant deep learning methods are fundamentally black-box systems that lack explanations for their inferences, significantly limiting their trustworthiness and adoption. Explainable AI (XAI) methods aim to overcome this challenge by providing explanations of the models' decision process. Such methods are often proposed and developed by engineers and scientists with a predominantly technical background and incorporate their assumptions about the existence, validity, and explanatory utility of different conceivable explanatory mechanisms. However, the basic concept of an explanation -- what it is, whether we can know it, whether it is absolute or relative -- is far from trivial and has been the subject of deep philosophical debate for millennia. As we point out here, the assumptions incorporated into different XAI methods are not harmless and have important consequences for the validity and interpretation of AI explanations in different domains. We investigate ontological and epistemological assumptions in explainability methods when they are applied to AI systems, meaning the assumptions we make about the existence of explanations and our ability to gain knowledge about those explanations. Our analysis shows how seemingly small technical changes to an XAI method may correspond to important differences in the underlying assumptions about explanations. We furthermore highlight the risks of ignoring the underlying onto-epistemological paradigm when choosing an XAI method for a given application, and we discuss how to select and adapt appropriate XAI methods for different domains of application.

Alessandro Betti, Marco Gori, Stefano Melacci et al.

This paper sustains the position that the time has come for thinking of learning machines that conquer visual skills in a truly human-like context, where a few human-like object supervisions are given by vocal interactions and pointing aids only. This likely requires new foundations on computational processes of vision with the final purpose of involving machines in tasks of visual description by living in their own visual environment under simple man-machine linguistic interactions. The challenge consists of developing machines that learn to see without needing to handle visual databases. This might open the doors to a truly orthogonal competitive track concerning deep learning technologies for vision which does not rely on the accumulation of huge visual databases.

Gui-Song Xia, Jian Ding, Ming Qian et al.

This report summarizes the results of Learning to Understand Aerial Images (LUAI) 2021 challenge held on ICCV 2021, which focuses on object detection and semantic segmentation in aerial images. Using DOTA-v2.0 and GID-15 datasets, this challenge proposes three tasks for oriented object detection, horizontal object detection, and semantic segmentation of common categories in aerial images. This challenge received a total of 146 registrations on the three tasks. Through the challenge, we hope to draw attention from a wide range of communities and call for more efforts on the problems of learning to understand aerial images.

Antonio Emanuele Cinà, Kathrin Grosse, Sebastiano Vascon et al.

Backdoor attacks inject poisoning samples during training, with the goal of forcing a machine learning model to output an attacker-chosen class when presented a specific trigger at test time. Although backdoor attacks have been demonstrated in a variety of settings and against different models, the factors affecting their effectiveness are still not well understood. In this work, we provide a unifying framework to study the process of backdoor learning under the lens of incremental learning and influence functions. We show that the effectiveness of backdoor attacks depends on: (i) the complexity of the learning algorithm, controlled by its hyperparameters; (ii) the fraction of backdoor samples injected into the training set; and (iii) the size and visibility of the backdoor trigger. These factors affect how fast a model learns to correlate the presence of the backdoor trigger with the target class. Our analysis unveils the intriguing existence of a region in the hyperparameter space in which the accuracy on clean test samples is still high while backdoor attacks are ineffective, thereby suggesting novel criteria to improve existing defenses.

Antonio Emanuele Cinà, Sebastiano Vascon, Ambra Demontis et al.

One of the most concerning threats for modern AI systems is data poisoning, where the attacker injects maliciously crafted training data to corrupt the system's behavior at test time. Availability poisoning is a particularly worrisome subset of poisoning attacks where the attacker aims to cause a Denial-of-Service (DoS) attack. However, the state-of-the-art algorithms are computationally expensive because they try to solve a complex bi-level optimization problem (the "hammer"). We observed that in particular conditions, namely, where the target model is linear (the "nut"), the usage of computationally costly procedures can be avoided. We propose a counter-intuitive but efficient heuristic that allows contaminating the training set such that the target system's performance is highly compromised. We further suggest a re-parameterization trick to decrease the number of variables to be optimized. Finally, we demonstrate that, under the considered settings, our framework achieves comparable, or even better, performances in terms of the attacker's objective while being significantly more computationally efficient.

Jian Ding, Nan Xue, Gui-Song Xia et al.

In the past decade, object detection has achieved significant progress in natural images but not in aerial images, due to the massive variations in the scale and orientation of objects caused by the bird's-eye view of aerial images. More importantly, the lack of large-scale benchmarks has become a major obstacle to the development of object detection in aerial images (ODAI). In this paper,we present a large-scale Dataset of Object deTection in Aerial images (DOTA) and comprehensive baselines for ODAI. The proposed DOTA dataset contains 1,793,658 object instances of 18 categories of oriented-bounding-box annotations collected from 11,268 aerial images. Based on this large-scale and well-annotated dataset, we build baselines covering 10 state-of-the-art algorithms with over 70 configurations, where the speed and accuracy performances of each model have been evaluated. Furthermore, we provide a code library for ODAI and build a website for evaluating different algorithms. Previous challenges run on DOTA have attracted more than 1300 teams worldwide. We believe that the expanded large-scale DOTA dataset, the extensive baselines, the code library and the challenges can facilitate the designs of robust algorithms and reproducible research on the problem of object detection in aerial images.

Kunping Yang, Gui-Song Xia, Zicheng Liu et al.

Given two multi-temporal aerial images, semantic change detection aims to locate the land-cover variations and identify their change types with pixel-wise boundaries. This problem is vital in many earth vision related tasks, such as precise urban planning and natural resource management. Existing state-of-the-art algorithms mainly identify the changed pixels by applying homogeneous operations on each input image and comparing the extracted features. However, in changed regions, totally different land-cover distributions often require heterogeneous features extraction procedures w.r.t each input. In this paper, we present an asymmetric siamese network (ASN) to locate and identify semantic changes through feature pairs obtained from modules of widely different structures, which involve areas of various sizes and apply different quantities of parameters to factor in the discrepancy across different land-cover distributions. To better train and evaluate our model, we create a large-scale well-annotated SEmantic Change detectiON Dataset (SECOND), while an Adaptive Threshold Learning (ATL) module and a Separated Kappa (SeK) coefficient are proposed to alleviate the influences of label imbalance in model training and evaluation. The experimental results demonstrate that the proposed model can stably outperform the state-of-the-art algorithms with different encoder backbones.

Antonio Emanuele Cinà, Alessandro Torcinovich, Marcello Pelillo

Clustering algorithms play a fundamental role as tools in decision-making and sensible automation processes. Due to the widespread use of these applications, a robustness analysis of this family of algorithms against adversarial noise has become imperative. To the best of our knowledge, however, only a few works have currently addressed this problem. In an attempt to fill this gap, in this work, we propose a black-box adversarial attack for crafting adversarial samples to test the robustness of clustering algorithms. We formulate the problem as a constrained minimization program, general in its structure and customizable by the attacker according to her capability constraints. We do not assume any information about the internal structure of the victim clustering algorithm, and we allow the attacker to query it as a service only. In the absence of any derivative information, we perform the optimization with a custom approach inspired by the Abstract Genetic Algorithm (AGA). In the experimental part, we demonstrate the sensibility of different single and ensemble clustering algorithms against our crafted adversarial samples on different scenarios. Furthermore, we perform a comparison of our algorithm with a state-of-the-art approach showing that we are able to reach or even outperform its performance. Finally, to highlight the general nature of the generated noise, we show that our attacks are transferable even against supervised algorithms such as SVMs, random forests, and neural networks.

Feliks Hibraj, Marcello Pelillo, Saverio Salzo et al.

Recently, classical kernel methods have been extended by the introduction of suitable tensor kernels so to promote sparsity in the solution of the underlying regression problem. Indeed, they solve an lp-norm regularization problem, with p=m/(m-1) and m even integer, which happens to be close to a lasso problem. However, a major drawback of the method is that storing tensors requires a considerable amount of memory, ultimately limiting its applicability. In this work we address this problem by proposing two advances. First, we directly reduce the memory requirement, by intriducing a new and more efficient layout for storing the data. Second, we use a Nystrom-type subsampling approach, which allows for a training phase with a smaller number of data points, so to reduce the computational cost. Experiments, both on synthetic and read datasets, show the effectiveness of the proposed improvements. Finally, we take case of implementing the cose in C++ so to further speed-up the computation.

Ismail Elezi, Sebastiano Vascon, Alessandro Torcinovich et al.

Deep metric learning has yielded impressive results in tasks such as clustering and image retrieval by leveraging neural networks to obtain highly discriminative feature embeddings, which can be used to group samples into different classes. Much research has been devoted to the design of smart loss functions or data mining strategies for training such networks. Most methods consider only pairs or triplets of samples within a mini-batch to compute the loss function, which is commonly based on the distance between embeddings. We propose Group Loss, a loss function based on a differentiable label-propagation method that enforces embedding similarity across all samples of a group while promoting, at the same time, low-density regions amongst data points belonging to different groups. Guided by the smoothness assumption that "similar objects should belong to the same group", the proposed loss trains the neural network for a classification task, enforcing a consistent labelling amongst samples within a class. We show state-of-the-art results on clustering and image retrieval on several datasets, and show the potential of our method when combined with other techniques such as ensembles

Sinem Aslan, Marcello Pelillo

The availability of large-scale data sets is an essential pre-requisite for deep learning based semantic segmentation schemes. Since obtaining pixel-level labels is extremely expensive, supervising deep semantic segmentation networks using low-cost weak annotations has been an attractive research problem in recent years. In this work, we explore the potential of Constrained Dominant Sets (CDS) for generating multi-labeled full mask predictions to train a fully convolutional network (FCN) for semantic segmentation. Our experimental results show that using CDS's yields higher-quality mask predictions compared to methods that have been adopted in the literature for the same purpose.

Sebastiano Vascon, Sinem Aslan, Alessandro Torcinovich et al.

Unsupervised domain adaptation (UDA) amounts to assigning class labels to the unlabeled instances of a dataset from a target domain, using labeled instances of a dataset from a related source domain. In this paper, we propose to cast this problem in a game-theoretic setting as a non-cooperative game and introduce a fully automatized iterative algorithm for UDA based on graph transduction games (GTG). The main advantages of this approach are its principled foundation, guaranteed termination of the iterative algorithms to a Nash equilibrium (which corresponds to a consistent labeling condition) and soft labels quantifying the uncertainty of the label assignment process. We also investigate the beneficial effect of using pseudo-labels from linear classifiers to initialize the iterative process. The performance of the resulting methods is assessed on publicly available object recognition benchmark datasets involving both shallow and deep features. Results of experiments demonstrate the suitability of the proposed game-theoretic approach for solving UDA tasks.

Leulseged Tesfaye Alemu, Marcello Pelillo, Mubarak Shah

In this work, we propose an end-to-end constrained clustering scheme to tackle the person re-identification (re-id) problem. Deep neural networks (DNN) have recently proven to be effective on person re-identification task. In particular, rather than leveraging solely a probe-gallery similarity, diffusing the similarities among the gallery images in an end-to-end manner has proven to be effective in yielding a robust probe-gallery affinity. However, existing methods do not apply probe image as a constraint, and are prone to noise propagation during the similarity diffusion process. To overcome this, we propose an intriguing scheme which treats person-image retrieval problem as a {\em constrained clustering optimization} problem, called deep constrained dominant sets (DCDS). Given a probe and gallery images, we re-formulate person re-id problem as finding a constrained cluster, where the probe image is taken as a constraint (seed) and each cluster corresponds to a set of images corresponding to the same person. By optimizing the constrained clustering in an end-to-end manner, we naturally leverage the contextual knowledge of a set of images corresponding to the given person-images. We further enhance the performance by integrating an auxiliary net alongside DCDS, which employs a multi-scale Resnet. To validate the effectiveness of our method we present experiments on several benchmark datasets and show that the proposed method can outperform state-of-the-art methods.

Fu-Dong Wang, Gui-Song Xia, Nan Xue et al.

Graph matching is an important and persistent problem in computer vision and pattern recognition for finding node-to-node correspondence between graph-structured data. However, as widely used, graph matching that incorporates pairwise constraints can be formulated as a quadratic assignment problem (QAP), which is NP-complete and results in intrinsic computational difficulties. In this paper, we present a functional representation for graph matching (FRGM) that aims to provide more geometric insights on the problem and reduce the space and time complexities of corresponding algorithms. To achieve these goals, we represent a graph endowed with edge attributes by a linear function space equipped with a functional such as inner product or metric, that has an explicit geometric meaning. Consequently, the correspondence between graphs can be represented as a linear representation map of that functional. Specifically, we reformulate the linear functional representation map as a new parameterization for Euclidean graph matching, which is associative with geometric parameters for graphs under rigid or nonrigid deformations. This allows us to estimate the correspondence and geometric deformations simultaneously. The use of the representation of edge attributes rather than the affinity matrix enables us to reduce the space complexity by two orders of magnitudes. Furthermore, we propose an efficient optimization strategy with low time complexity to optimize the objective function. The experimental results on both synthetic and real-world datasets demonstrate that the proposed FRGM can achieve state-of-the-art performance.

Battista Biggio, Ignazio Pillai, Samuel Rota Bulò et al.

Clustering algorithms have been increasingly adopted in security applications to spot dangerous or illicit activities. However, they have not been originally devised to deal with deliberate attack attempts that may aim to subvert the clustering process itself. Whether clustering can be safely adopted in such settings remains thus questionable. In this work we propose a general framework that allows one to identify potential attacks against clustering algorithms, and to evaluate their impact, by making specific assumptions on the adversary's goal, knowledge of the attacked system, and capabilities of manipulating the input data. We show that an attacker may significantly poison the whole clustering process by adding a relatively small percentage of attack samples to the input data, and that some attack samples may be obfuscated to be hidden within some existing clusters. We present a case study on single-linkage hierarchical clustering, and report experiments on clustering of malware samples and handwritten digits.

Ismail Elezi, Lukas Tuggener, Marcello Pelillo et al.

This paper gives an overview of our current Optical Music Recognition (OMR) research. We recently released the OMR dataset \emph{DeepScores} as well as the object detection method \emph{Deep Watershed Detector}. We are currently taking some additional steps to improve both of them. Here we summarize current and future efforts, aimed at improving usefulness on real-world task and tackling extreme class imbalance.

Sebastiano Vascon, Ylenia Parin, Eis Annavini et al.

For most animal species, quick and reliable identification of visual objects is critical for survival. This applies also to rodents, which, in recent years, have become increasingly popular models of visual functions. For this reason in this work we analyzed how various properties of visual objects are represented in rat primary visual cortex (V1). The analysis has been carried out through supervised (classification) and unsupervised (clustering) learning methods. We assessed quantitatively the discrimination capabilities of V1 neurons by demonstrating how photometric properties (luminosity and object position in the scene) can be derived directly from the neuronal responses.

Sinem Aslan, Sebastiano Vascon, Marcello Pelillo

Recognizing the type of an ancient coin requires theoretical expertise and years of experience in the field of numismatics. Our goal in this work is automatizing this time consuming and demanding task by a visual classification framework. Specifically, we propose to model ancient coin image classification using Graph Transduction Games (GTG). GTG casts the classification problem as a non-cooperative game where the players (the coin images) decide their strategies (class labels) according to the choices made by the others, which results with a global consensus at the final labeling. Experiments are conducted on the only publicly available dataset which is composed of 180 images of 60 types of Roman coins. We demonstrate that our approach outperforms the literature work on the same dataset with the classification accuracy of 73.6% and 87.3% when there are one and two images per class in the training set, respectively.

Leulseged Tesfaye Alemu, Marcello Pelillo

Aggregating different image features for image retrieval has recently shown its effectiveness. While highly effective, though, the question of how to uplift the impact of the best features for a specific query image persists as an open computer vision problem. In this paper, we propose a computationally efficient approach to fuse several hand-crafted and deep features, based on the probabilistic distribution of a given membership score of a constrained cluster in an unsupervised manner. First, we introduce an incremental nearest neighbor (NN) selection method, whereby we dynamically select k-NN to the query. We then build several graphs from the obtained NN sets and employ constrained dominant sets (CDS) on each graph G to assign edge weights which consider the intrinsic manifold structure of the graph, and detect false matches to the query. Finally, we elaborate the computation of feature positive-impact weight (PIW) based on the dispersive degree of the characteristics vector. To this end, we exploit the entropy of a cluster membership-score distribution. In addition, the final NN set bypasses a heuristic voting scheme. Experiments on several retrieval benchmark datasets show that our method can improve the state-of-the-art result.

Tewodros Mulugeta Dagnew, Dalia Coppi, Marcello Pelillo et al.

Semi-supervised learning is a popular class of techniques to learn from labeled and unlabeled data. The paper proposes an application of a recently proposed approach of graph transduction that exploits game theoretic notions to the problem of multiple people tracking. Within the proposed framework, targets are considered as players of a multi-player non-cooperative game. The equilibria of the game is considered as a consistent labeling solution and thus an estimation of the target association in the sequence of frames. Patches of persons are extracted from the video frames using a HOG based detector and their similarity is modeled using distances among their covariance matrices. The solution we propose achieves satisfactory results on video surveillance datasets. The experiments show the robustness of the method even with a heavy unbalance between the number of labeled and unlabeled input patches.

Ismail Elezi, Alessandro Torcinovich, Sebastiano Vascon et al.

A major impediment to the application of deep learning to real-world problems is the scarcity of labeled data. Small training sets are in fact of no use to deep networks as, due to the large number of trainable parameters, they will very likely be subject to overfitting phenomena. On the other hand, the increment of the training set size through further manual or semi-automatic labellings can be costly, if not possible at times. Thus, the standard techniques to address this issue are transfer learning and data augmentation, which consists of applying some sort of "transformation" to existing labeled instances to let the training set grow in size. Although this approach works well in applications such as image classification, where it is relatively simple to design suitable transformation operators, it is not obvious how to apply it in more structured scenarios. Motivated by the observation that in virtually all application domains it is easy to obtain unlabeled data, in this paper we take a different perspective and propose a \emph{label augmentation} approach. We start from a small, curated labeled dataset and let the labels propagate through a larger set of unlabeled data using graph transduction techniques. This allows us to naturally use (second-order) similarity information which resides in the data, a source of information which is typically neglected by standard augmentation techniques. In particular, we show that by using known game theoretic transductive processes we can create larger and accurate enough labeled datasets which use results in better trained neural networks. Preliminary experiments are reported which demonstrate a consistent improvement over standard image classification datasets.

Feliks Hibraj, Sebastiano Vascon, Thilo Stadelmann et al.

Speaker clustering is the task of forming speaker-specific groups based on a set of utterances. In this paper, we address this task by using Dominant Sets (DS). DS is a graph-based clustering algorithm with interesting properties that fits well to our problem and has never been applied before to speaker clustering. We report on a comprehensive set of experiments on the TIMIT dataset against standard clustering techniques and specific speaker clustering methods. Moreover, we compare performances under different features by using ones learned via deep neural network directly on TIMIT and other ones extracted from a pre-trained VGGVox net. To asses the stability, we perform a sensitivity analysis on the free parameters of our method, showing that performance is stable under parameter changes. The extensive experimentation carried out confirms the validity of the proposed method, reporting state-of-the-art results under three different standard metrics. We also report reference baseline results for speaker clustering on the entire TIMIT dataset for the first time.

Lukas Tuggener, Ismail Elezi, Jürgen Schmidhuber et al.

We present the DeepScores dataset with the goal of advancing the state-of-the-art in small objects recognition, and by placing the question of object recognition in the context of scene understanding. DeepScores contains high quality images of musical scores, partitioned into 300,000 sheets of written music that contain symbols of different shapes and sizes. With close to a hundred millions of small objects, this makes our dataset not only unique, but also the largest public dataset. DeepScores comes with ground truth for object classification, detection and semantic segmentation. DeepScores thus poses a relevant challenge for computer vision in general, beyond the scope of optical music recognition (OMR) research. We present a detailed statistical analysis of the dataset, comparing it with other computer vision datasets like Caltech101/256, PASCAL VOC, SUN, SVHN, ImageNet, MS-COCO, smaller computer vision datasets, as well as with other OMR datasets. Finally, we provide baseline performances for object classification and give pointers to future research based on this dataset.

Gui-Song Xia, Xiang Bai, Jian Ding et al.

Object detection is an important and challenging problem in computer vision. Although the past decade has witnessed major advances in object detection in natural scenes, such successes have been slow to aerial imagery, not only because of the huge variation in the scale, orientation and shape of the object instances on the earth's surface, but also due to the scarcity of well-annotated datasets of objects in aerial scenes. To advance object detection research in Earth Vision, also known as Earth Observation and Remote Sensing, we introduce a large-scale Dataset for Object deTection in Aerial images (DOTA). To this end, we collect $2806$ aerial images from different sensors and platforms. Each image is of the size about 4000-by-4000 pixels and contains objects exhibiting a wide variety of scales, orientations, and shapes. These DOTA images are then annotated by experts in aerial image interpretation using $15$ common object categories. The fully annotated DOTA images contains $188,282$ instances, each of which is labeled by an arbitrary (8 d.o.f.) quadrilateral To build a baseline for object detection in Earth Vision, we evaluate state-of-the-art object detection algorithms on DOTA. Experiments demonstrate that DOTA well represents real Earth Vision applications and are quite challenging.

Eyasu Zemene, Leulseged Tesfaye Alemu, Marcello Pelillo

Image segmentation has come a long way since the early days of computer vision, and still remains a challenging task. Modern variations of the classical (purely bottom-up) approach, involve, e.g., some form of user assistance (interactive segmentation) or ask for the simultaneous segmentation of two or more images (co-segmentation). At an abstract level, all these variants can be thought of as "constrained" versions of the original formulation, whereby the segmentation process is guided by some external source of information. In this paper, we propose a new approach to tackle this kind of problems in a unified way. Our work is based on some properties of a family of quadratic optimization problems related to dominant sets, a well-known graph-theoretic notion of a cluster which generalizes the concept of a maximal clique to edge-weighted graphs. In particular, we show that by properly controlling a regularization parameter which determines the structure and the scale of the underlying problem, we are in a position to extract groups of dominant-set clusters that are constrained to contain predefined elements. In particular, we shall focus on interactive segmentation and co-segmentation (in both the unsupervised and the interactive versions). The proposed algorithm can deal naturally with several type of constraints and input modality, including scribbles, sloppy contours, and bounding boxes, and is able to robustly handle noisy annotations on the part of the user. Experiments on standard benchmark datasets show the effectiveness of our approach as compared to state-of-the-art algorithms on a variety of natural images under several input conditions and constraints.

Yonatan Tariku Tesfaye, Eyasu Zemene, Andrea Prati et al.

In this paper, a unified three-layer hierarchical approach for solving tracking problems in multiple non-overlapping cameras is proposed. Given a video and a set of detections (obtained by any person detector), we first solve within-camera tracking employing the first two layers of our framework and, then, in the third layer, we solve across-camera tracking by merging tracks of the same person in all cameras in a simultaneous fashion. To best serve our purpose, a constrained dominant sets clustering (CDSC) technique, a parametrized version of standard quadratic optimization, is employed to solve both tracking tasks. The tracking problem is caste as finding constrained dominant sets from a graph. In addition to having a unified framework that simultaneously solves within- and across-camera tracking, the third layer helps link broken tracks of the same person occurring during within-camera tracking. In this work, we propose a fast algorithm, based on dynamics from evolutionary game theory, which is efficient and salable to large-scale real-world applications.

Marco Fiorucci, Alessandro Torcinovich, Manuel Curado et al.

In this paper we analyze the practical implications of Szemerédi's regularity lemma in the preservation of metric information contained in large graphs. To this end, we present a heuristic algorithm to find regular partitions. Our experiments show that this method is quite robust to the natural sparsification of proximity graphs. In addition, this robustness can be enforced by graph densification.

Eyasu Zemene, Yonatan Tariku, Haroon Idrees et al.

This paper presents a new approach for the challenging problem of geo-locating an image using image matching in a structured database of city-wide reference images with known GPS coordinates. We cast the geo-localization as a clustering problem on local image features. Akin to existing approaches on the problem, our framework builds on low-level features which allow partial matching between images. For each local feature in the query image, we find its approximate nearest neighbors in the reference set. Next, we cluster the features from reference images using Dominant Set clustering, which affords several advantages over existing approaches. First, it permits variable number of nodes in the cluster which we use to dynamically select the number of nearest neighbors (typically coming from multiple reference images) for each query feature based on its discrimination value. Second, as we also quantify in our experiments, this approach is several orders of magnitude faster than existing approaches. Thus, we obtain multiple clusters (different local maximizers) and obtain a robust final solution to the problem using multiple weak solutions through constrained Dominant Set clustering on global image features, where we enforce the constraint that the query image must be included in the cluster. This second level of clustering also bypasses heuristic approaches to voting and selecting the reference image that matches to the query. We evaluated the proposed framework on an existing dataset of 102k street view images as well as a new dataset of 300k images, and show that it outperforms the state-of-the-art by 20% and 7%, respectively, on the two datasets.

Marcello Pelillo, Ismail Elezi, Marco Fiorucci

Introduced in the mid-1970's as an intermediate step in proving a long-standing conjecture on arithmetic progressions, Szemerédi's regularity lemma has emerged over time as a fundamental tool in different branches of graph theory, combinatorics and theoretical computer science. Roughly, it states that every graph can be approximated by the union of a small number of random-like bipartite graphs called regular pairs. In other words, the result provides us a way to obtain a good description of a large graph using a small amount of data, and can be regarded as a manifestation of the all-pervading dichotomy between structure and randomness. In this paper we will provide an overview of the regularity lemma and its algorithmic aspects, and will discuss its relevance in the context of pattern recognition research.

Rocco Tripodi, Sebastiano Vascon, Marcello Pelillo

In this article we propose a method to refine the clustering results obtained with the nonnegative matrix factorization (NMF) technique, imposing consistency constraints on the final labeling of the data. The research community focused its effort on the initialization and on the optimization part of this method, without paying attention to the final cluster assignments. We propose a game theoretic framework in which each object to be clustered is represented as a player, which has to choose its cluster membership. The information obtained with NMF is used to initialize the strategy space of the players and a weighted graph is used to model the interactions among the players. These interactions allow the players to choose a cluster which is coherent with the clusters chosen by similar players, a property which is not guaranteed by NMF, since it produces a soft clustering of the data. The results on common benchmarks show that our model is able to improve the performances of many NMF formulations.

Samuel Rota Bulò, Battista Biggio, Ignazio Pillai et al.

In spam and malware detection, attackers exploit randomization to obfuscate malicious data and increase their chances of evading detection at test time; e.g., malware code is typically obfuscated using random strings or byte sequences to hide known exploits. Interestingly, randomization has also been proposed to improve security of learning algorithms against evasion attacks, as it results in hiding information about the classifier to the attacker. Recent work has proposed game-theoretical formulations to learn secure classifiers, by simulating different evasion attacks and modifying the classification function accordingly. However, both the classification function and the simulated data manipulations have been modeled in a deterministic manner, without accounting for any form of randomization. In this work, we overcome this limitation by proposing a randomized prediction game, namely, a non-cooperative game-theoretic formulation in which the classifier and the attacker make randomized strategy selections according to some probability distribution defined over the respective strategy set. We show that our approach allows one to improve the trade-off between attack detection and false alarms with respect to state-of-the-art secure classifiers, even against attacks that are different from those hypothesized during design, on application examples including handwritten digit recognition, spam and malware detection.

Eyasu Zemene, Marcello Pelillo

We propose a new approach to interactive image segmentation based on some properties of a family of quadratic optimization problems related to dominant sets, a well-known graph-theoretic notion of a cluster which generalizes the concept of a maximal clique to edge-weighted graphs. In particular, we show that by properly controlling a regularization parameter which determines the structure and the scale of the underlying problem, we are in a position to extract groups of dominant-set clusters which are constrained to contain user-selected elements. The resulting algorithm can deal naturally with any type of input modality, including scribbles, sloppy contours, and bounding boxes, and is able to robustly handle noisy annotations on the part of the user. Experiments on standard benchmark datasets show the effectiveness of our approach as compared to state-of-the-art algorithms on a variety of natural images under several input conditions.