Deep Learning approaches have recently raised the bar in many fields, from Natural Language Processing to Computer Vision, by leveraging large amounts of data. However, they could fail when the retrieved information is not enough to it the vast number of parameters, frequently resulting in overfitting and, therefore, in poor generalizability. Few-Shot Learning aims at designing models which can effectively operate in a scarce data regime, yielding learning strategies that only need few supervised examples to be trained. These procedures are of both practical and theoretical importance, as they are crucial for many real-life scenarios in which data is either costly or even impossible to retrieve. Moreover, they bridge the distance between current data-hungry models and human-like generalization capability. Computer Vision offers various tasks which can be few-shot inherent, such as person re-identification. This survey, which to the best of our knowledge is the first tackling this problem, is focused on Few-Shot Object Detection, which has received far less attention compared to Few-Shot Classification due to the intrinsic challenge level. In this regard, this review presents an extensive description of the approaches that have been tested in the current literature, discussing their pros and cons, and classifying them according to a rigorous taxonomy.

Few-Shot Object Detection: A Survey / Antonelli, Simone; Avola, Danilo; Cinque, Luigi; Crisostomi, Donato; Luca Foresti, Gian; Galasso, Fabio; Marini, MARCO RAOUL; Mecca, Alessio; Pannone, Daniele. - In: ACM COMPUTING SURVEYS. - ISSN 0360-0300. - (2022). [10.1145/3519022]

Few-Shot Object Detection: A Survey

Simone Antonelli;Danilo Avola;Luigi Cinque;Donato Crisostomi;Fabio Galasso;Marco Raoul Marini;Alessio Mecca;Daniele Pannone
2022

Abstract

Deep Learning approaches have recently raised the bar in many fields, from Natural Language Processing to Computer Vision, by leveraging large amounts of data. However, they could fail when the retrieved information is not enough to it the vast number of parameters, frequently resulting in overfitting and, therefore, in poor generalizability. Few-Shot Learning aims at designing models which can effectively operate in a scarce data regime, yielding learning strategies that only need few supervised examples to be trained. These procedures are of both practical and theoretical importance, as they are crucial for many real-life scenarios in which data is either costly or even impossible to retrieve. Moreover, they bridge the distance between current data-hungry models and human-like generalization capability. Computer Vision offers various tasks which can be few-shot inherent, such as person re-identification. This survey, which to the best of our knowledge is the first tackling this problem, is focused on Few-Shot Object Detection, which has received far less attention compared to Few-Shot Classification due to the intrinsic challenge level. In this regard, this review presents an extensive description of the approaches that have been tested in the current literature, discussing their pros and cons, and classifying them according to a rigorous taxonomy.
2022
computer vision, machine learning, meta-learning, few-shot object detection
01 Pubblicazione su rivista::01a Articolo in rivista
Few-Shot Object Detection: A Survey / Antonelli, Simone; Avola, Danilo; Cinque, Luigi; Crisostomi, Donato; Luca Foresti, Gian; Galasso, Fabio; Marini, MARCO RAOUL; Mecca, Alessio; Pannone, Daniele. - In: ACM COMPUTING SURVEYS. - ISSN 0360-0300. - (2022). [10.1145/3519022]
File allegati a questo prodotto
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1621756
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 52
  • ???jsp.display-item.citation.isi??? 37
social impact