Paolo Garza

Daniele Rege Cambrin, Isaac Corley, Paolo Garza

Estimating global tree canopy height is crucial for forest conservation and climate change applications. However, capturing high-resolution ground truth canopy height using LiDAR is expensive and not available globally. An efficient alternative is to train a canopy height estimator to operate on single-view remotely sensed imagery. The primary obstacle to this approach is that these methods require significant training data to generalize well globally and across uncommon edge cases. Recent monocular depth estimation foundation models have show strong zero-shot performance even for complex scenes. In this paper we leverage the representations learned by these models to transfer to the remote sensing domain for measuring canopy height. Our findings suggest that our proposed Depth Any Canopy, the result of fine-tuning the Depth Anything v2 model for canopy height estimation, provides a performant and efficient solution, surpassing the current state-of-the-art with superior or comparable performance using only a fraction of the computational resources and parameters. Furthermore, our approach requires less than \$1.30 in compute and results in an estimated carbon footprint of 0.14 kgCO2. Code, experimental results, and model checkpoints are openly available at https://github.com/DarthReca/depth-any-canopy.

Daniele Rege Cambrin, Eleonora Poeta, Eliana Pastor et al.

Segmentation of crop fields is essential for enhancing agricultural productivity, monitoring crop health, and promoting sustainable practices. Deep learning models adopted for this task must ensure accurate and reliable predictions to avoid economic losses and environmental impact. The newly proposed Kolmogorov-Arnold networks (KANs) offer promising advancements in the performance of neural networks. This paper analyzes the integration of KAN layers into the U-Net architecture (U-KAN) to segment crop fields using Sentinel-2 and Sentinel-1 satellite images and provides an analysis of the performance and explainability of these networks. Our findings indicate a 2\% improvement in IoU compared to the traditional full-convolutional U-Net model in fewer GFLOPs. Furthermore, gradient-based explanation techniques show that U-KAN predictions are highly plausible and that the network has a very high ability to focus on the boundaries of cultivated areas rather than on the areas themselves. The per-channel relevance analysis also reveals that some channels are irrelevant to this task.

Daniele Rege Cambrin, Giuseppe Gallipoli, Irene Benedetto et al.

Large Language Models (LLMs) have demonstrated impressive performance across various tasks. However, current training approaches combine standard cross-entropy loss with extensive data, human feedback, or ad hoc methods to enhance performance. These solutions are often not scalable or feasible due to their associated costs, complexity, or resource requirements. This study investigates the use of established semantic segmentation loss functions in natural language generation to create a versatile, practical, and scalable solution for fine-tuning different architectures. We evaluate their effectiveness in solving Math Word Problems and question answering across different models of varying sizes. For the analyzed tasks, we found that the traditional Cross-Entropy loss represents a sub-optimal choice, while models trained to minimize alternative (task-dependent) losses, such as Focal or Lovász, achieve a mean improvement of +42% on exact match without requiring additional data or human feedback. These findings suggest a promising pathway for more efficient and accessible training processes.

Daniele Rege Cambrin, Gabriele Scaffidi Militone, Luca Colomba et al.

Designing effective game tutorials is crucial for a smooth learning curve for new players, especially in games with many rules and complex core mechanics. Evaluating the effectiveness of these tutorials usually requires multiple iterations with testers who have no prior knowledge of the game. Recent Vision-Language Models (VLMs) have demonstrated significant capabilities in understanding and interpreting visual content. VLMs can analyze images, provide detailed insights, and answer questions about their content. They can recognize objects, actions, and contexts in visual data, making them valuable tools for various applications, including automated game testing. In this work, we propose an automated game-testing solution to evaluate the quality of game tutorials. Our approach leverages VLMs to analyze frames from video game tutorials, answer relevant questions to simulate human perception, and provide feedback. This feedback is compared with expected results to identify confusing or problematic scenes and highlight potential errors for developers. In addition, we publish complete tutorial videos and annotated frames from different game versions used in our tests. This solution reduces the need for extensive manual testing, especially by speeding up and simplifying the initial development stages of the tutorial to improve the final game experience.

Daniele Rege Cambrin, Isaac Corley, Paolo Garza et al.

Earthquakes are commonly estimated using physical seismic stations, however, due to the installation requirements and costs of these stations, global coverage quickly becomes impractical. An efficient and lower-cost alternative is to develop machine learning models to globally monitor earth observation data to pinpoint regions impacted by these natural disasters. However, due to the small amount of historically recorded earthquakes, this becomes a low-data regime problem requiring algorithmic improvements to achieve peak performance when learning to regress earthquake magnitude. In this paper, we propose to pose the estimation of earthquake magnitudes as a metric-learning problem, training models to not only estimate earthquake magnitude from Sentinel-1 satellite imagery but to additionally rank pairwise samples. Our experiments show at max a 30%+ improvement in MAE over prior regression-only based methods, particularly transformer-based architectures.

Moreno La Quatra, Alkis Koudounas, Lorenzo Vaiani et al. · gatech

Limited diversity in standardized benchmarks for evaluating audio representation learning (ARL) methods may hinder systematic comparison of current methods' capabilities. We present ARCH, a comprehensive benchmark for evaluating ARL methods on diverse audio classification domains, covering acoustic events, music, and speech. ARCH comprises 12 datasets, that allow us to thoroughly assess pre-trained SSL models of different sizes. ARCH streamlines benchmarking of ARL techniques through its unified access to a wide range of domains and its ability to readily incorporate new datasets and models. To address the current lack of open-source, pre-trained models for non-speech audio, we also release new pre-trained models that demonstrate strong performance on non-speech datasets. We argue that the presented wide-ranging evaluation provides valuable insights into state-of-the-art ARL methods, and is useful to pinpoint promising research directions.

Daniele Rege Cambrin, Paolo Garza

Earthquake monitoring is necessary to promptly identify the affected areas, the severity of the events, and, finally, to estimate damages and plan the actions needed for the restoration process. The use of seismic stations to monitor the strength and origin of earthquakes is limited when dealing with remote areas (we cannot have global capillary coverage). Identification and analysis of all affected areas is mandatory to support areas not monitored by traditional stations. Using social media images in crisis management has proven effective in various situations. However, they are still limited by the possibility of using communication infrastructures in case of an earthquake and by the presence of people in the area. Moreover, social media images and messages cannot be used to estimate the actual severity of earthquakes and their characteristics effectively. The employment of satellites to monitor changes around the globe grants the possibility of exploiting instrumentation that is not limited by the visible spectrum, the presence of land infrastructures, and people in the affected areas. In this work, we propose a new dataset composed of images taken from Sentinel-1 and a new series of tasks to help monitor earthquakes from a new detailed view. Coupled with the data, we provide a series of traditional machine learning and deep learning models as baselines to assess the effectiveness of ML-based models in earthquake analysis.

Yihao Ding, Lorenzo Vaiani, Caren Han et al.

This paper presents a groundbreaking multimodal, multi-task, multi-teacher joint-grained knowledge distillation model for visually-rich form document understanding. The model is designed to leverage insights from both fine-grained and coarse-grained levels by facilitating a nuanced correlation between token and entity representations, addressing the complexities inherent in form documents. Additionally, we introduce new inter-grained and cross-grained loss functions to further refine diverse multi-teacher knowledge distillation transfer process, presenting distribution gaps and a harmonised understanding of form documents. Through a comprehensive evaluation across publicly available form document understanding datasets, our proposed model consistently outperforms existing baselines, showcasing its efficacy in handling the intricate structures and content of visually complex form documents.

Tailai Song, Paolo Garza, Michela Meo et al.

The Real-time Transport Protocol (RTP)-based real-time communications (RTC) applications, exemplified by video conferencing, have experienced an unparalleled surge in popularity and development in recent years. In pursuit of optimizing their performance, the prediction of Quality of Service (QoS) metrics emerges as a pivotal endeavor, bolstering network monitoring and proactive solutions. However, contemporary approaches are confined to individual RTP flows and metrics, falling short in relationship capture and computational efficiency. To this end, we propose Packet-to-Prediction (P2P), a novel deep learning (DL) framework that hinges on raw packets to simultaneously process concurrent RTP flows and perform end-to-end prediction of multiple QoS metrics. Specifically, we implement a streamlined architecture, namely length-free Transformer with cross and neighbourhood attention, capable of handling an unlimited number of RTP flows, and employ a multi-task learning paradigm to forecast four key metrics in a single shot. Our work is based on extensive traffic collected during real video calls, and conclusively, P2P excels comparative models in both prediction performance and temporal efficiency.

Daniele Rege Cambrin, Luca Colomba, Paolo Garza

In crisis management and remote sensing, image segmentation plays a crucial role, enabling tasks like disaster response and emergency planning by analyzing visual data. Neural networks are able to analyze satellite acquisitions and determine which areas were affected by a catastrophic event. The problem in their development in this context is the data scarcity and the lack of extensive benchmark datasets, limiting the capabilities of training large neural network models. In this paper, we propose a novel methodology, namely Magnifier, to improve segmentation performance with limited data availability. The Magnifier methodology is applicable to any existing encoder-decoder architecture, as it extends a model by merging information at different contextual levels through a dual-encoder approach: a local and global encoder. Magnifier analyzes the input data twice using the dual-encoder approach. In particular, the local and global encoders extract information from the same input at different granularities. This allows Magnifier to extract more information than the other approaches given the same set of input images. Magnifier improves the quality of the results of +2.65% on average IoU while leading to a restrained increase in terms of the number of trainable parameters compared to the original model. We evaluated our proposed approach with state-of-the-art burned area segmentation models, demonstrating, on average, comparable or better performances in less than half of the GFLOPs.

Luca Colomba, Paolo Garza

Satellite missions and Earth Observation (EO) systems represent fundamental assets for environmental monitoring and the timely identification of catastrophic events, long-term monitoring of both natural resources and human-made assets, such as vegetation, water bodies, forests as well as buildings. Different EO missions enables the collection of information on several spectral bandwidths, such as MODIS, Sentinel-1 and Sentinel-2. Thus, given the recent advances of machine learning, computer vision and the availability of labeled data, researchers demonstrated the feasibility and the precision of land-use monitoring systems and remote sensing image classification through the use of deep neural networks. Such systems may help domain experts and governments in constant environmental monitoring, enabling timely intervention in case of catastrophic events (e.g., forest wildfire in a remote area). Despite the recent advances in the field of computer vision, many works limit their analysis on Convolutional Neural Networks (CNNs) and, more recently, to vision transformers (ViTs). Given the recent successes of Graph Neural Networks (GNNs) on non-graph data, such as time-series and images, we investigate the performances of a recent Vision GNN architecture (ViG) applied to the task of land cover classification. The experimental results show that ViG achieves state-of-the-art performances in multiclass and multilabel classification contexts, surpassing both ViT and ResNet on large-scale benchmarks.

Daniele Rege Cambrin, Luca Cagliero, Paolo Garza

Summarizing multiple disaster-relevant data streams simultaneously is particularly challenging as existing Retrieve&Re-ranking strategies suffer from the inherent redundancy of multi-stream data and limited scalability in a multi-query setting. This work proposes an online approach to crisis timeline generation based on weak annotation with Deep Q-Networks. It selects on-the-fly the relevant pieces of text without requiring neither human annotations nor content re-ranking. This makes the inference time independent of the number of input queries. The proposed approach also incorporates a redundancy filter into the reward function to effectively handle cross-stream content overlaps. The achieved ROUGE and BERTScore results are superior to those of best-performing models on the CrisisFACTS 2022 benchmark.

Mattia Ottoborgo, Daniele Rege Cambrin, Paolo Garza

Cooking recipes are complex procedures that require not only a fluent and factual text, but also accurate timing, temperature, and procedural coherence, as well as the correct composition of ingredients. Standard training procedures are primarily based on cross-entropy and focus solely on fluency. Building on RECIPE-NLG, we investigate the use of several composite objectives and present a new topological loss that represents ingredient lists as point clouds in embedding space, minimizing the divergence between predicted and gold ingredients. Using both standard NLG metrics and recipe-specific metrics, we find that our loss significantly improves ingredient- and action-level metrics. Meanwhile, the Dice loss excels in time/temperature precision, and the mixed loss yields competitive trade-offs with synergistic gains in quantity and time. A human preference analysis supports our finding, showing our model is preferred in 62% of the cases.

Daniele Rege Cambrin, Lorenzo Vaiani, Giuseppe Gallipoli et al.

Retrieving relevant imagery from vast satellite archives is crucial for applications like disaster response and long-term climate monitoring. However, most text-to-image retrieval systems are limited to RGB data, failing to exploit the unique physical information captured by other sensors, such as the all-weather structural sensitivity of Synthetic Aperture Radar (SAR) or the spectral signatures in optical multispectral data. To bridge this gap, we introduce CrisisLandMark, a new large-scale corpus of over 647,000 Sentinel-1 SAR and Sentinel-2 multispectral images paired with structured textual annotations for land cover, land use, and crisis events harmonized from authoritative land cover systems (CORINE and Dynamic World) and crisis-specific sources. We then present CLOSP (Contrastive Language Optical SAR Pretraining), a novel framework that uses text as a bridge to align unpaired optical and SAR images into a unified embedding space. Our experiments show that CLOSP achieves a new state-of-the-art, improving retrieval nDGC@1000 by 54% over existing models. Additionally, we find that the unified training strategy overcomes the inherent difficulty of interpreting SAR imagery by transferring rich semantic knowledge from the optical domain with indirect interaction. Furthermore, GeoCLOSP, which integrates geographic coordinates into our framework, creates a powerful trade-off between generality and specificity: while the CLOSP excels at general semantic tasks, the GeoCLOSP becomes a specialized expert for retrieving location-dependent crisis events and rare geographic features. This work highlights that the integration of diverse sensor data and geographic context is essential for unlocking the full potential of remote sensing archives.

Daniele Rege Cambrin, Eleonora Poeta, Eliana Pastor et al.

Forecasting surface water dynamics is crucial for water resource management and climate change adaptation. However, the field lacks comprehensive datasets and standardized benchmarks. In this paper, we introduce HydroChronos, a large-scale, multi-modal spatiotemporal dataset for surface water dynamics forecasting designed to address this gap. We couple the dataset with three forecasting tasks. The dataset includes over three decades of aligned Landsat 5 and Sentinel-2 imagery, climate data, and Digital Elevation Models for diverse lakes and rivers across Europe, North America, and South America. We also propose AquaClimaTempo UNet, a novel spatiotemporal architecture with a dedicated climate data branch, as a strong benchmark baseline. Our model significantly outperforms a Persistence baseline for forecasting future water dynamics by +14% and +11% F1 across change detection and direction of change classification tasks, and by +0.1 MAE on the magnitude of change regression. Finally, we conduct an Explainable AI analysis to identify the key climate variables and input channels that influence surface water change, providing insights to inform and guide future modeling efforts.

Luca Barco, Giacomo Blanco, Gaetano Chiriaco et al.

3D semantic segmentation plays a critical role in urban modelling, enabling detailed understanding and mapping of city environments. In this paper, we introduce Turin3D: a new aerial LiDAR dataset for point cloud semantic segmentation covering an area of around 1.43 km2 in the city centre of Turin with almost 70M points. We describe the data collection process and compare Turin3D with others previously proposed in the literature. We did not fully annotate the dataset due to the complexity and time-consuming nature of the process; however, a manual annotation process was performed on the validation and test sets, to enable a reliable evaluation of the proposed techniques. We first benchmark the performances of several point cloud semantic segmentation models, trained on the existing datasets, when tested on Turin3D, and then improve their performances by applying a semi-supervised learning technique leveraging the unlabelled training set. The dataset will be publicly available to support research in outdoor point cloud segmentation, with particular relevance for self-supervised and semi-supervised learning approaches given the absence of ground truth annotations for the training set.

Daniele Rege Cambrin, Luca Colomba, Paolo Garza

Forest wildfires represent one of the catastrophic events that, over the last decades, caused huge environmental and humanitarian damages. In addition to a significant amount of carbon dioxide emission, they are a source of risk to society in both short-term (e.g., temporary city evacuation due to fire) and long-term (e.g., higher risks of landslides) cases. Consequently, the availability of tools to support local authorities in automatically identifying burned areas plays an important role in the continuous monitoring requirement to alleviate the aftereffects of such catastrophic events. The great availability of satellite acquisitions coupled with computer vision techniques represents an important step in developing such tools. This paper introduces a novel open dataset that tackles the burned area delineation problem, a binary segmentation problem applied to satellite imagery. The presented resource consists of pre- and post-fire Sentinel-2 L2A acquisitions of California forest fires that took place starting in 2015. Raster annotations were generated from the data released by California's Department of Forestry and Fire Protection. Moreover, in conjunction with the dataset, we release three different baselines based on spectral indexes analyses, SegFormer, and U-Net models.

Luca Venturini, Elena Baralis, Paolo Garza

Supervised learning algorithms are nowadays successfully scaling up to datasets that are very large in volume, leveraging the potential of in-memory cluster-computing Big Data frameworks. Still, massive datasets with a number of large-domain categorical features are a difficult challenge for any classifier. Most off-the-shelf solutions cannot cope with this problem. In this work we introduce DAC, a Distributed Associative Classifier. DAC exploits ensemble learning to distribute the training of an associative classifier among parallel workers and improve the final quality of the model. Furthermore, it adopts several novel techniques to reach high scalability without sacrificing quality, among which a preventive pruning of classification rules in the extraction phase based on Gini impurity. We ran experiments on Apache Spark, on a real large-scale dataset with more than 4 billion records and 800 million distinct categories. The results showed that DAC improves on a state-of-the-art solution in both prediction quality and execution time. Since the generated model is human-readable, it can not only classify new records, but also allow understanding both the logic behind the prediction and the properties of the model, becoming a useful aid for decision makers.