Nico Catalano

Nico Catalano

PhD Candidate in Computer Science
Computer Vision & AI
AIRLab, Politecnico di Milano

Posts by Collection

portfolio

publications

A comparative study of Fourier transform and CycleGAN as domain adaptation techniques for weed segmentation

Published in Smart Agricultural Technology, 2023

Automatic weed identification is becoming increasingly important in the Precision Agriculture field as a fundamental capability for targeted spraying or mechanical weed destruction. Targeted weed elimination reduces herbicides’ use and thus lowers the environmental impact of treatments. Convolutional Neural Networks are one of the most successful techniques to automatically detect weeds on RGB images. Such models require a high amount of labeled data to obtain satisfying detection performance. The agricultural context presents a high degree of variability, and it is thus unfeasible to expect a representative dataset for each specific condition that can appear in the fields. Domain Adaptation techniques are exploited to maintain high detection performance in different field conditions, lowering the need for labeled data. This study presents a comparison of the two main style transfer techniques for performing domain adaptation, that is, the Fourier Transform and the CycleGAN architecture. We used these techniques to reduce the domain gap in two use cases: one with images collected by different robots with different cameras and another with images collected by the same platform in different years. We show how, in the first case, the CycleGAN architecture attains satisfying performance and beats the simpler Fourier Transform. Instead, in the second case, all the tested DA techniques struggle to reach baseline performance. We also show how introducing a loss based on phase discrepancy in the CycleGAN architecture stabilizes the training and improves the performance. Moreover, we release a new dataset of labeled agricultural images and the code of our experiments for the reproducibility of the results and comparison with future works.

Recommended citation: Bertoglio, R., Mazzucchelli, A., Catalano, N., & Matteucci, M. (2023). A comparative study of Fourier transform and CycleGAN as domain adaptation techniques for weed segmentation. Smart agricultural technology, 4, 100188.
Download Paper

Surgical fine-tuning for grape bunch segmentation under visual domain shifts

Published in 2023 European Conference on Mobile Robots (ECMR)., 2023

Mobile robots will play a crucial role in the transition towards sustainable agriculture. To autonomously and effectively monitor the state of plants, robots ought to be equipped with visual perception capabilities that are robust to the rapid changes that characterise agricultural settings. In this paper, we focus on the challenging task of segmenting grape bunches from images collected by mobile robots in vineyards. In this context, we present the first study that applies surgical fine-tuning to instance segmentation tasks. We show how selectively tuning only specific model layers can support the adaptation of pre-trained Deep Learning models to newlycollected grape images that introduce visual domain shifts, while also substantially reducing the number of tuned parameters.

Recommended citation: Chiatti, A., Bertoglio, R., Catalano, N., Gatti, M., & Matteucci, M. (2023, September). Surgical fine-tuning for grape bunch segmentation under visual domain shifts. In 2023 European Conference on Mobile Robots (ECMR) (pp. 1-7). IEEE.
Download Paper

Few shot semantic segmentation: a review of methodologies and open challenges

Published in Arxiv, 2023

Semantic segmentation, vital for applications ranging from autonomous driving to robotics, faces significant challenges in domains where collecting large annotated datasets is difficult or prohibitively expensive. In such contexts, such as medicine and agriculture, the scarcity of training images hampers progress. Introducing Few-Shot Semantic Segmentation, a novel task in computer vision, which aims at designing models capable of segmenting new semantic classes with only a few examples. This paper consists of a comprehensive survey of Few-Shot Semantic Segmentation, tracing its evolution and exploring various model designs, from the more popular conditional and prototypical networks to the more niche latent space optimization methods, presenting also the new opportunities offered by recent foundational models. Through a chronological narrative, we dissect influential trends and methodologies, providing insights into their strengths and limitations. A temporal timeline offers a visual roadmap, marking key milestones in the field’s progression. Complemented by quantitative analyses on benchmark datasets and qualitative showcases of seminal works, this survey equips readers with a deep understanding of the topic. By elucidating current challenges, state-of-the-art models, and prospects, we aid researchers and practitioners in navigating the intricacies of Few-Shot Semantic Segmentation and provide ground for future development.

Recommended citation: Catalano, Nico, and Matteo Matteucci. "Few shot semantic segmentation: a review of methodologies and open challenges."
Download Paper

Tackling Environmental Variability: Few Shot Segmentation for Domain-Adaptive Weed Segmentation in Agricultural Robotics

Published in 2024 IEEE 20th International Conference on Automation Science and Engineering (CASE), 2024

This paper investigates the application of Few Shot Segmentation techniques in addressing weed management challenges within agricultural robotics. Traditional methods, such as indiscriminate herbicide spraying, pose environmental and economic concerns, emphasize the necessity of developing automated precision procedures. Semantic Segmentation models can offer significant advancements in weed management within agricultural robotics but can be negatively impacted by domain shifts, often requiring adaptation, hindering the development of the field. In this context, we propose a Few Shot Segmentation-based approach for precise weed segmentation in corn and bean cultivations. Our model, adapted from PFENet, exhibits robust performance across varying environmental conditions, mitigating domain shift issues. Evaluation on the ROSE dataset demonstrates the model’s reliability and generalizability, highlighting the potential of Few Shot Segmentation in advancing agricultural robotics technologies.

Recommended citation: Catalano, N., Leone, M., & Matteucci, M. (2024, August). Tackling Environmental Variability: Few Shot Segmentation for Domain-Adaptive Weed Segmentation in Agricultural Robotics. In 2024 IEEE 20th International Conference on Automation Science and Engineering (CASE) (pp. 583-588). IEEE.
Download Paper

More than the Sum of Its Parts: Ensembling Backbone Networks for Few-Shot Segmentation

Published in 2024 International Joint Conference on Neural Networks (IJCNN), 2024

Semantic segmentation is a key prerequisite to robust image understanding for applications in Artificial In- telligence and Robotics. Few Shot Segmentation, in particular, concerns the extension and optimization of traditional segmen- tation methods in challenging conditions where limited training examples are available. A predominant approach in Few Shot Segmentation is to rely on a single backbone for visual feature extraction. Choosing which backbone to leverage is a deciding factor contributing to the overall performance. In this work, we interrogate on whether fusing features from different backbones can improve the ability of Few Shot Segmentation models to capture richer visual features. To tackle this question, we propose and compare two ensembling techniques—Independent Voting and Feature Fusion. Among the available Few Shot Segmentation methods, we implement the proposed ensembling techniques on PANet. The module dedicated to predicting segmentation masks from the backbone embeddings in PANet avoids trainable parameters, creating a controlled ‘in vitro’ setting for isolating the impact of different ensembling strategies. Leveraging the complementary strengths of different backbones, our approach outperforms the original single-backbone PANet across standard benchmarks even in challenging one-shot learning scenarios. Specifically, it achieved a performance improvement of +7.37% on PASCAL-5i and of +10.68% on COCO-20i in the top- performing scenario where three backbones are combined. These results, together with the qualitative inspection of the predicted subject masks, suggest that relying on multiple backbones in PANet leads to a more comprehensive feature representation, thus expediting the successful application of Few Shot Segmentation methods in challenging, data-scarce environments

Recommended citation: Catalano, N., Maranelli, A., Chiatti, A., & Matteucci, M. (2024, June). More than the Sum of Its Parts: Ensembling Backbone Networks for Few-Shot Segmentation. In 2024 International Joint Conference on Neural Networks (IJCNN) (pp. 1-8). IEEE.
Download Paper

talks

teaching