Searcharxiv⌕ Search

arXiv subjects

Giacomo Boracchi

Publications and source records attributed to Giacomo Boracchi.

At least 19 recordsLinked to original sources

Unlocking Cross-Attention in Label-Scarce Regimes: A Weakly Supervised Approach for Video Semantic Segmentation

Weakly Supervised Video Semantic Segmentation (WS-VSS) aims to learn temporally consistent semantic object masks in videos using only video-level labels. While fully supervised models successfully learn temporal relationships by means of cross-attention, training these temporal weights under weak supervision is unstable and even pushes the model below its single-frame baseline. Therefore, existing WS-VSS methods exploit temporal consistency by relying on external priors, such as optical flow. Unfortunately these cues are non-semantic, computationally expensive and noisy, degrading the supervisory signal. Instead of supervising attention weights directly or using external priors, we propose MemCAM, a WS-VSS transformer framework that learns temporal cross-attention directly through feature-space self-supervision. MemCAM introduces a CAM Propagation Algorithm that synthesizes a supervisory signal by propagating past CAMs according to patch-level feature similarities in the latent space. Specifically, we constrain their induced CAMs through a consistency objective between predicted and propagated maps, stabilizing temporal attention learning. Experiments on the YouTube-Objects v2.2 and WS$^2$ datasets demonstrate that MemCAM consistently outperforms the temporal localization and segmentation performance of WS-VSS alternatives, showing that cross-attention can be effectively trained in label-scarce video settings through internal self-supervision.

cs.CV↗

Malware families discovery via Open-Set Recognition on Android manifest permissions

Malware are malicious programs that are grouped into families based on their penetration technique, source code, and other characteristics. Classifying malware programs into their respective families is essential for building effective defenses against cyber threats. Machine learning models have a huge potential in malware detection on mobile devices, as malware families can be recognized by classifying permission data extracted from Android manifest files. Still, the malware classification task is challenging due to the high-dimensional nature of permission data and the limited availability of training samples. In particular, the steady emergence of new malware families makes it impossible to acquire a comprehensive training set covering all the malware classes. In this work, we present a malware classification system that, on top of classifying known malware, detects new ones. In particular, we combine an open-set recognition technique developed within the computer vision community, namely MaxLogit, with a tree-based Gradient Boosting classifier, which is particularly effective in classifying high-dimensional data. Our solution turns out to be very practical, as it can be seamlessly employed in a standard classification workflow, and efficient, as it adds minimal computational overhead. Experiments on public and proprietary datasets demonstrate the potential of our solution, which has been deployed in a business environment.

cs.CR↗

DenseTwins: Dense Modality Decoupling for Multimodal Self-Supervision

Multimodal perception is central to many computer vision applications, including robotics and autonomous driving, where different sensing modalities provide complementary cues. Self-supervised learning offers a scalable solution for exploiting large amounts of unlabeled multimodal data. However, existing methods either neglect modality-specific information by enforcing feature-space alignment between modalities or learn only global representations without preserving spatial structure. We propose DenseTwins, a multimodal self-supervised framework that learns dense representations by explicitly decoupling the dense feature space into shared and modality-specific components. The proposed approach combines dense cross-modal correspondences with redundancy-reduction objectives, enabling the model to capture both shared semantics and modality-specific cues within a structured dense embedding space. DenseTwins jointly optimizes an intra-modal objective across augmented views and a cross-modal objective that aligns shared features while decorrelating modality-specific information. We evaluate DenseTwins across multiple multimodal benchmarks and sensing setups, achieving state-of-the-art or competitive performance across multimodal self-supervised baselines. Code available at: https://github.com/CarloSgaravatti/DenseTwins.

cs.CV↗

MiCaDe: Online LiDAR-Camera Miscalibration Change Detection for Autonomous Driving

Reliable multi-sensor perception in autonomous vehicles requires accurate calibration between cameras and LiDAR. However, calibration drift is often unavoidable in long-term deployments: vibrations, thermal effects, and minor mechanical shocks may alter the relative pose between sensors, leading to systematic errors in downstream fusion tasks. We propose MiCaDe (Miscalibration Change Detection), an online solution detecting when the extrinsic LiDAR-camera calibration parameters are no longer accurate by means of sequential change detection. MiCaDe requires no calibration targets, or modification of the perception stack, providing low false-alarm rates with negligible computational overhead. Our key insight is that 3D and 2D bounding boxes produced by standard object detectors should remain geometrically consistent under correct calibration. By matching cross-modal detections, we derive geometric consistency metrics that serve as sensitive indicators of extrinsic drift. These metrics are aggregated into fixed-size batches and scored against a reference distribution, producing a likelihood stream that is monitored by a Change Point Model (CPM). Crucially, the CPM accumulates statistical evidence over time, enabling detection of subtle drifts that would otherwise go unnoticed. Experiments on multiple long-sequence datasets and on a real-world dataset with physically induced miscalibration confirm reliable detection under diverse conditions. Code available at: https://github.com/CarloSgaravatti/MiCaDe.

cs.CV↗

Weakly Supervised Polar Low Segmentation in Sentinel-1 SAR Imagery

Polar lows are intense maritime cyclones that form rapidly at high latitudes. Deep learning can detect them in Synthetic Aperture Radar (SAR) imagery, but pixel-level segmentation remains an open challenge. No pixel-level masks are available for training, and a polar low's extent is inherently subjective, with diffuse boundaries that even experts delineate inconsistently. We propose Constrained Region Erasing with Soft Targets (CREST), a Weakly Supervised Semantic Segmentation (WSSS) framework that generates masks solely from image-level labels. Our approach builds on Adversarial Erasing (AER), which iteratively mines discriminative regions, erases them, and retrains a classifier to reveal complementary cues that become pseudo-labels for segmentation. However, standard AER also collects irrelevant background features, degrading pseudo-label quality. CREST addresses this with (i) a Constrained Ordinal Region Expansion (CORE) module that encodes the spatial-connectedness prior of polar lows, constraining region expansion from a high-confidence seed, and (ii) a Dynamic Bootstrapping (DB) loss that treats the mining order as a proxy for label reliability, attenuating supervision from noisier, later-mined regions. On Sentinel-1 SAR data, CREST follows the cyclone structure more closely than standard AER, and returns a multi-class rather than binary mask whose classes indicate the reliability assigned to each region. We further evaluate on BUS-UCLM breast ultrasound and PASCAL VOC person data, whose targets satisfy the same connectedness prior but come with the dense masks the SAR data lacks. On both datasets, CREST performs better than the equivalent AER pipeline under identical settings.

cs.CV↗

SAR Vessel Detection and Gross Tonnage Estimation from Heterogeneous Datasets for Dark Vessel Identification

Detecting vessels engaging in illegal activities is of paramount importance for maritime security. One of the major goals is to detect dark vessels, ships that disable their transponders to evade surveillance. Deep Learning (DL) models can detect vessels in Synthetic Aperture Radar (SAR) images, enabling maritime traffic analysis regardless of weather or visibility conditions. However, to detect potential dark vessels, a DL model must select only those that are required to carry a transponder based on their Gross Tonnage (GT). Unfortunately, no public SAR dataset is available for training an end-to-end DL model for vessel detection and GT regression. In this work, we present a framework that leverages heterogeneous image and tabular datasets to solve this task. Our solution combines a multi-task DL framework for predicting the location, vessel type, and physical dimensions of ships, cascaded with a non-parametric model for predicting GT from vessel size and category. We perform GT regression by a KNN that measures sample similarity using a hybrid Euclidean and categorical distance. Experiments show that our solution can predict multiple outputs while remaining competitive with state-of-the-art models on individual subtasks, thus enabling the identification of dark vessels. We publish our code on GitHub https://github.com/PaltrinieriDavide/vesseldetection.

cs.CV↗

Cell Phantom Video Generation in Elliptical Fourier Descriptor Domain

Training Deep Neural Networks for tracking individual cells in biomedical videos requires a large amount of annotated data. The annotation of videos for cell tracking is very time consuming and often requires domain expertise; this explains the limited availability of public annotated data to address important medical problems like tissue repair or cancer treatment. Generating synthetic videos along with their Ground Truth annotations is a promising solution that relies, as a foundational first step, on the synthesis of single cell annotations (or phantoms). Phantoms need to be time consistent, as they have to replicate biological processes that are specific to the cell types. In this work, we propose a novel framework for generating videos of cell phantoms in the Elliptical Fourier Descriptors (EFDs) domain, a compact and geometrically interpretable representation for 2D closed contours. We represent the cell phantom evolution as a multivariate time series of EFD coefficients, introducing a strong prior for cell morphology and enabling the efficient generation of sequences that evolve coherently in time. Our experimental validation proves that modelling the temporal evolution in EFD space enables the generation of biologically plausible phantom videos. Our method can be used in generative pipelines for synthesizing annotated data for cell tracking, thus strongly mitigating the annotation effort for creating new datasets. Our code is available for download here: https://github.com/FrancescoBenedetto99/efd-cell-video-gen.

cs.CV↗

Accurate Simulation Pipeline for Passive Single-Photon Imaging

Single-Photon Avalanche Diodes (SPADs) are new and promising imaging sensors. These sensors are sensitive enough to detect individual photons hitting each pixel, with extreme temporal resolution and without readout noise. Thus, SPADs stand out as an optimal choice for low-light imaging. Due to the high price and limited availability of SPAD sensors, the demand for an accurate data simulation pipeline is substantial. Indeed, the scarcity of SPAD datasets hinders the development of SPAD-specific processing algorithms and impedes the training of learning-based solutions. In this paper, we present a comprehensive SPAD simulation pipeline and validate it with multiple experiments using two recent commercial SPAD sensors. Our simulator is used to generate the SPAD-MNIST, a single-photon version of the seminal MNIST dataset, to investigate the effectiveness of convolutional neural network (CNN) classifiers on reconstructed fluxes, even at extremely low light conditions, e.g., 5 mlux. We also assess the performance of classifiers exclusively trained on simulated data on real images acquired from SPAD sensors at different light conditions. The synthetic dataset encompasses different SPAD imaging modalities and is made available for download. Project page: https://boracchi.faculty.polimi.it/Projects/SPAD-MNIST.html.

physics.ins-det↗

LCF3D: A Robust and Real-Time Late-Cascade Fusion Framework for 3D Object Detection in Autonomous Driving

Accurately localizing 3D objects like pedestrians, cyclists, and other vehicles is essential in Autonomous Driving. To ensure high detection performance, Autonomous Vehicles complement RGB cameras with LiDAR sensors, but effectively combining these data sources for 3D object detection remains challenging. We propose LCF3D, a novel sensor fusion framework that combines a 2D object detector on RGB images with a 3D object detector on LiDAR point clouds. By leveraging multimodal fusion principles, we compensate for inaccuracies in the LiDAR object detection network. Our solution combines two key principles: (i) late fusion, to reduce LiDAR False Positives by matching LiDAR 3D detections with RGB 2D detections and filtering out unmatched LiDAR detections; and (ii) cascade fusion, to recover missed objects from LiDAR by generating new 3D frustum proposals corresponding to unmatched RGB detections. Experiments show that LCF3D is beneficial for domain generalization, as it turns out to be successful in handling different sensor configurations between training and testing domains. LCF3D achieves significant improvements over LiDAR-based methods, particularly for challenging categories like pedestrians and cyclists in the KITTI dataset, as well as motorcycles and bicycles in nuScenes. Code can be downloaded from: https://github.com/CarloSgaravatti/LCF3D.

cs.CV↗

Promptable Foundation Models for SAR Remote Sensing: Adapting the Segment Anything Model for Snow Avalanche Segmentation

Remote sensing solutions for avalanche segmentation and mapping are key to supporting risk forecasting and mitigation in mountain regions. Synthetic Aperture Radar (SAR) imagery from Sentinel-1 can be effectively used for this task, but training an effective detection model requires gathering a large dataset with high-quality annotations from domain experts, which is prohibitively time-consuming. In this work, we aim to facilitate and accelerate the annotation of SAR images for avalanche mapping. We build on the Segment Anything Model (SAM), a segmentation foundation model trained on natural images, and tailor it to Sentinel-1 SAR data. Adapting SAM to our use-case requires addressing several domain-specific challenges: (i) domain mismatch, since SAM was not trained on satellite/SAR imagery; (ii) input adaptation, because SAR products typically provide more than three channels, while SAM is constrained to RGB images; (iii) robustness to imprecise prompts that can affect target identification and degrade the segmentation quality, an issue exacerbated in small, low-contrast avalanches; and (iv) training efficiency, since standard fine-tuning is computationally demanding for SAM. We tackle these challenges through a combination of adapters to mitigate the domain gap, multiple encoders to handle multi-channel SAR inputs, prompt-engineering strategies to improve avalanche localization accuracy, and a training algorithm that limits the training time of the encoder, which is recognized as the major bottleneck. We integrate the resulting model into an annotation tool and show experimentally that it speeds up the annotation of SAR images.

cs.CV↗

One target to align them all: LiDAR, RGB and event cameras extrinsic calibration for Autonomous Driving

We present a novel multi-modal extrinsic calibration framework designed to simultaneously estimate the relative poses between event cameras, LiDARs, and RGB cameras, with particular focus on the challenging event camera calibration. Core of our approach is a novel 3D calibration target, specifically designed and constructed to be concurrently perceived by all three sensing modalities. The target encodes features in planes, ChArUco, and active LED patterns, each tailored to the unique characteristics of LiDARs, RGB cameras, and event cameras respectively. This unique design enables a one-shot, joint extrinsic calibration process, in contrast to existing approaches that typically rely on separate, pairwise calibrations. Our calibration pipeline is designed to accurately calibrate complex vision systems in the context of autonomous driving, where precise multi-sensor alignment is critical. We validate our approach through an extensive experimental evaluation on a custom built dataset, recorded with an advanced autonomous driving sensor setup, confirming the accuracy and robustness of our method.

cs.CV↗

Convolutional Set Transformer

We introduce the Convolutional Set Transformer (CST), a novel neural architecture designed to process image sets of arbitrary cardinality that are visually heterogeneous yet share high-level semantics - such as a common category, scene, or concept. Existing set-input networks, e.g., Deep Sets and Set Transformer, are limited to vector inputs and cannot directly handle 3D image tensors. As a result, they must be cascaded with a feature extractor, typically a CNN, which encodes images into embeddings before the set-input network can model inter-image relationships. In contrast, CST operates directly on 3D image tensors, performing feature extraction and contextual modeling simultaneously, thereby enabling synergies between the two processes. This design yields superior performance in tasks such as Set Classification and Set Anomaly Detection and further provides native compatibility with CNN explainability methods such as Grad-CAM, unlike competing approaches that remain opaque. Finally, we show that CSTs can be pre-trained on large-scale datasets and subsequently adapted to new domains and tasks through standard Transfer Learning schemes. To support further research, we release CST-15, a CST backbone pre-trained on ImageNet (https://github.com/chinefed/convolutional-set-transformer).

cs.CV↗

Preference Isolation Forest for Structure-based Anomaly Detection

We address the problem of detecting anomalies as samples that do not conform to structured patterns represented by low-dimensional manifolds. To this end, we conceive a general anomaly detection framework called Preference Isolation Forest (PIF), that combines the benefits of adaptive isolation-based methods with the flexibility of preference embedding. The key intuition is to embed the data into a high-dimensional preference space by fitting low-dimensional manifolds, and to identify anomalies as isolated points. We propose three isolation approaches to identify anomalies: $i$) Voronoi-iForest, the most general solution, $ii$) RuzHash-iForest, that avoids explicit computation of distances via Local Sensitive Hashing, and $iii$) Sliding-PIF, that leverages a locality prior to improve efficiency and effectiveness.

cs.LG↗

A Deep Learning Pipeline for Solid Waste Detection in Remote Sensing Images

Improper solid waste management represents both a serious threat to ecosystem health and a significant source of revenues for criminal organizations perpetrating environmental crimes. This issue can be mitigated thanks to the increasing availability of Very-High-Resolution Remote Sensing (VHR RS) images. Modern image-analysis tools support automated photo-interpretation and large territory scanning in search of illegal waste disposal sites. This paper illustrates a semi-automatic waste detection pipeline, developed in collaboration with a regional environmental protection agency, for detecting candidate illegal dumping sites in VHR RS images. To optimize the effectiveness of the waste detector at the core of the pipeline, extensive experiments evaluate such design choices as the network architecture, the ground resolution and geographic span of the input images, as well as the pretraining procedures. The best model attains remarkable performance, achieving 92.02 % F1-Score and 94.56 % Accuracy. A generalization study assesses the performance variation when the detector processes images from various territories substantially different from the one used during training, incurring only a moderate performance loss, namely an average 5.1 % decrease in the F1-Score. Finally, an exercise in which expert photo-interpreters compare the effort required to scan large territories with and without support from the waste detector assesses the practical benefit of introducing a computer-aided image analysis tool in a professional environmental protection agency. Results show that a reduction of up to 30 % of the time spent for waste site detection can be attained.

cs.CV↗

WS$^2$: Weakly Supervised Segmentation using Before-After Supervision in Waste Sorting

In industrial quality control, to visually recognize unwanted items within a moving heterogeneous stream, human operators are often still indispensable. Waste-sorting stands as a significant example, where operators on multiple conveyor belts manually remove unwanted objects to select specific materials. To automate this recognition problem, computer vision systems offer great potential in accurately identifying and segmenting unwanted items in such settings. Unfortunately, considering the multitude and the variety of sorting tasks, fully supervised approaches are not a viable option to address this challange, as they require extensive labeling efforts. Surprisingly, weakly supervised alternatives that leverage the implicit supervision naturally provided by the operator in his removal action are relatively unexplored. In this paper, we define the concept of Before-After Supervision, illustrating how to train a segmentation network by leveraging only the visual differences between images acquired \textit{before} and \textit{after} the operator. To promote research in this direction, we introduce WS$^2$ (Weakly Supervised segmentation for Waste-Sorting), the first multiview dataset consisting of more than 11 000 high-resolution video frames captured on top of a conveyor belt, including "before" and "after" images. We also present a robust end-to-end pipeline, used to benchmark several state-of-the-art weakly supervised segmentation methods on WS$^2$.

cs.CV↗

Biasing Frontier-Based Exploration with Saliency Areas

Autonomous exploration is a widely studied problem where a robot incrementally builds a map of a previously unknown environment. The robot selects the next locations to reach using an exploration strategy. To do so, the robot has to balance between competing objectives, like exploring the entirety of the environment, while being as fast as possible. Most exploration strategies try to maximise the explored area to speed up exploration; however, they do not consider that parts of the environment are more important than others, as they lead to the discovery of large unknown areas. We propose a method that identifies \emph{saliency areas} as those areas that are of high interest for exploration, by using saliency maps obtained from a neural network that, given the current map, implements a termination criterion to estimate whether the environment can be considered fully-explored or not. We use saliency areas to bias some widely used exploration strategies, showing, with an extensive experimental campaign, that this knowledge can significantly influence the behavior of the robot during exploration.

cs.RO↗

Hashing for Structure-based Anomaly Detection

We focus on the problem of identifying samples in a set that do not conform to structured patterns represented by low-dimensional manifolds. An effective way to solve this problem is to embed data in a high dimensional space, called Preference Space, where anomalies can be identified as the most isolated points. In this work, we employ Locality Sensitive Hashing to avoid explicit computation of distances in high dimensions and thus improve Anomaly Detection efficiency. Specifically, we present an isolation-based anomaly detection technique designed to work in the Preference Space which achieves state-of-the-art performance at a lower computational cost. Code is publicly available at https://github.com/ineveLoppiliF/Hashing-for-Structure-based-Anomaly-Detection.

cs.LG↗

MultiLink: Multi-class Structure Recovery via Agglomerative Clustering and Model Selection

We address the problem of recovering multiple structures of different classes in a dataset contaminated by noise and outliers. In particular, we consider geometric structures defined by a mixture of underlying parametric models (e.g. planes and cylinders, homographies and fundamental matrices), and we tackle the robust fitting problem by preference analysis and clustering. We present a new algorithm, termed MultiLink, that simultaneously deals with multiple classes of models. MultiLink combines on-the-fly model fitting and model selection in a novel linkage scheme that determines whether two clusters are to be merged. The resulting method features many practical advantages with respect to methods based on preference analysis, being faster, less sensitive to the inlier threshold, and able to compensate limitations deriving from hypotheses sampling. Experiments on several public datasets demonstrate that Multi-Link favourably compares with state of the art alternatives, both in multi-class and single-class problems. Code is publicly made available for download.

cs.LG↗