Lorenzo Papa

Dr. Lorenzo Papa

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 April 2024 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Open access
LPLorenzo Papa
Lorenzo Papa
Paolo RussoPaolo Russo
Paolo Russo
Irene AmeriniIrene Amerini
Irene Amerini
LZLuping Zhou
Luping Zhou
Vision Transformer (ViT) architectures are becoming increasingly popular and widely employed to tackle computer vision applications. Their main feature is the capacity to extract global information through the self-attention mechanism, outperforming earlier convolutional neural networks. However, ViT deployment and performance have grown steadily with their size, number of trainable parameters, and operations. Furthermore, self-attention's computational and memory cost quadratically increases with the image resolution. Generally speaking, it is challenging to employ these architectures in real-world applications due to many hardware and environmental restrictions, such as processing and computational capabilities. Therefore, this survey investigates the most efficient methodologies to ensure sub-optimal estimation performances. More in detail, four efficient categories will be analyzed: compact architecture, pruning, knowledge distillation, and quantization strategies. Moreover, a new metric called Efficient Error Rate has been introduced in order to normalize and compare models’ features that affect hardware devices at inference time, such as the number of parameters, bits, FLOPs, and model size. Summarizing, this paper first mathematically defines the strategies used to make Vision Transformer efficient, describes and discusses state-of-the-art methodologies, and analyzes their performances over different application scenarios. Toward the end of this paper, we also discuss open challenges and promising research directions.

16 September 2024 in Computer Vision and Image Understanding
Verified
Journal Article
Open access
AAAndrea Alfarano
Andrea Alfarano
LMLuca Maiano
Luca Maiano
LPLorenzo Papa
Lorenzo Papa
IAIrene Amerini
Irene Amerini

22 March 2023 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Open access
LPLorenzo Papa
Lorenzo Papa
Paolo RussoPaolo Russo
Paolo Russo
Irene AmeriniIrene Amerini
Irene Amerini
Depth estimation is a fundamental knowledge for autonomous systems that need to assess their own state and perceive the surrounding environment. Deep learning algorithms for depth estimation have gained significant interest in recent years, owing to the potential benefits of this methodology in overcoming the limitations of active depth sensing systems. Moreover, due to the low cost and size of monocular cameras, researchers have focused their attention on monocular depth estimation (MDE), which consists in estimating a dense depth map from a single RGB video frame. State of the art MDE models typically rely on vision transformers (ViT) architectures that are highly deep and complex, making them unsuitable for fast inference on devices with hardware constraints. Purposely, in this paper, we address the problem of exploiting ViT in MDE on embedded devices. Those systems are usually characterized by limited memory capabilities and low-power CPU/GPU. We propose METER, a novel lightweight vision transformer architecture capable of achieving state of the art estimations and low latency inference performances on the considered embedded hardwares: NVIDIA Jetson TX1 and NVIDIA Jetson Nano. We provide a solution consisting of three alternative configurations of METER, a novel loss function to balance pixel estimation and reconstruction of image details, and a new data augmentation strategy to improve the overall final predictions. The proposed method outperforms previous lightweight works over the two benchmark datasets: the indoor NYU Depth v2 and the outdoor KITTI.

25 April 2022 in IEEE Access
Verified
Journal Article
Open access
LPLorenzo Papa
Lorenzo Papa
EAEdoardo Alati
Edoardo Alati
Paolo RussoPaolo Russo
Paolo Russo
Irene AmeriniIrene Amerini
Irene Amerini
The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene understanding and visual odometry, which are key components in autonomous and robotic systems. Approaches based on the state of the art vision transformer architectures are extremely deep and complex not suitable for real-time inference operations on edge and autonomous systems equipped with low resources (i.e. robot indoor navigation and surveillance). This paper presents SPEED, a Separable Pyramidal pooling EncodEr-Decoder architecture designed to achieve real-time frequency performances on multiple hardware platforms. The proposed model is a fast-throughput deep architecture for MDE able to obtain depth estimations with high accuracy from low resolution images using minimum hardware resources (i.e. edge devices). Our encoder-decoder model exploits two depthwise separable pyramidal pooling layers, which allow to increase the inference frequency while reducing the overall computational complexity. The proposed method performs better than other fast-throughput architectures in terms of both accuracy and frame rates, achieving real-time performances over cloud CPU, TPU and the NVIDIA Jetson TX1 on two indoor benchmarks: the NYU Depth v2 and the DIML Kinect v2 datasets.

29 July 2023
Verified
Book Chapter
Closed access
PDF file
LMLuca Maiano
Luca Maiano
LPLorenzo Papa
Lorenzo Papa
KVKetbjano Vocaj
Ketbjano Vocaj
Irene AmeriniIrene Amerini
Irene Amerini

17 May 2024 in IEEE Security & Privacy
Verified
Journal Article
Open access
LMLuca Maiano
Luca Maiano
ABAlexandra Benova
Alexandra Benova
LPLorenzo Papa
Lorenzo Papa
MSMara Stockner
Mara Stockner
MMMichela Marchetti
Michela Marchetti
Irene AmeriniIrene Amerini
Irene Amerini
This article delves into the intricate process of artificial intelligence-generated content detection, shedding light on automated detectors’ challenges and revealing human detection biases, strengths, and weaknesses.